test

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd073ce7d3ded2ea1a04231ab1c6ffb0abae46b0468d17b885481f876693387
+size 1418184

Pyramids/Pyramids-1000048.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd073ce7d3ded2ea1a04231ab1c6ffb0abae46b0468d17b885481f876693387
+size 1418184

Pyramids/Pyramids-1000048.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c94be496af329fbb145c6df8c86e5262400e4e0fbb94faea124776e644c149
+size 8650990

Pyramids/Pyramids-499909.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ad750e80d6926e40044a316d20eadd282f854e8d9882af7e92ea4d1d140697
+size 1418184

Pyramids/Pyramids-499909.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7e85da98aaf81e2846ed22f59559dc05b44dced06df28b3bfe2b5b23eb1fb3
+size 8650990

Pyramids/Pyramids-999920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd073ce7d3ded2ea1a04231ab1c6ffb0abae46b0468d17b885481f876693387
+size 1418184

Pyramids/Pyramids-999920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56207731146b8afa5683ee7f88079a538fa7fb014d48c2206f874639f94bf21c
+size 8650990

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c94be496af329fbb145c6df8c86e5262400e4e0fbb94faea124776e644c149
+size 8650990

Pyramids/events.out.tfevents.1683117637.3f6063605010.4145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6909e470a998a2e60ad3fd9a555e752bc48bae534a73a48acd30b0571cc54d45
+size 323390

README.md

@@ -1,10 +1,10 @@
 ---
 library_name: ml-agents
 tags:
-- SnowballTarget
+- Pyramids
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-SnowballTarget
+- ML-Agents-Pyramids
 ---
 
   # **ppo** Agent playing **SnowballTarget**

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 100000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
     init_path: null
-    keep_checkpoints: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 100000
-    time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -64,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,14 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.12
+Multi-casting "[IP] 172.28.0.12 [Port] 55504 [Flags] 2 [Guid] 893103470 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
 Unable to load player prefs
-Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -34,10 +36,31 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.180 seconds
+- Completed reload, in  0.095 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -45,85 +68,90 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.953504 ms
+UnloadTime: 0.823717 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
-Memory Statistics:
+PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 2696 frames, [16.0 KB-32.0 KB]: 45 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7623 frames, [32.0 KB-64.0 KB]: 9289 frames, [64.0 KB-128.0 KB]: 1859 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 198 B
-      Overflow Count 0
-    [ALLOC_TEMP_Loading.PreloadManager]
-      Initial Block Size 256.0 KB
-      Current Block Size 304.0 KB
-      Peak Allocated Bytes 228.9 KB
-      Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 12]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_BatchDeleteObjects]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -143,48 +171,64 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 13116
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 2742 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 5.9 MB
+      Peak Block count 3
+      Peak Allocated memory 30.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 2742 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.9 MB
+      Peak Allocated memory 22.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -211,52 +255,63 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1949 frames, [64.0 KB-128.0 KB]: 793 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18771 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.7 KB
+      Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 2742 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18772 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 2742 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 2741 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18771 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 2742 frames
+      Peak usage frame count: [0-1.0 KB]: 18772 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 2742 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18772 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18772 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1683119745872,"processId":4163,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,214 +1,250 @@
 {
     "name": "root",
     "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.7562263011932373,
-            "min": 1.7562263011932373,
-            "max": 2.8640341758728027,
-            "count": 10
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.5534970760345459,
+            "min": 0.5534970760345459,
+            "max": 1.413807988166809,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 18082.10546875,
-            "min": 17038.705078125,
-            "max": 29362.078125,
-            "count": 10
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 16835.16796875,
+            "min": 16835.16796875,
+            "max": 42889.27734375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 99960.0,
-            "min": 9952.0,
-            "max": 99960.0,
-            "count": 10
+        "Pyramids.Step.mean": {
+            "value": 989976.0,
+            "min": 29876.0,
+            "max": 989976.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 99960.0,
-            "min": 9952.0,
-            "max": 99960.0,
-            "count": 10
+        "Pyramids.Step.sum": {
+            "value": 989976.0,
+            "min": 29876.0,
+            "max": 989976.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 8.264595985412598,
-            "min": 0.4249187707901001,
-            "max": 8.264595985412598,
-            "count": 10
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.2775384783744812,
+            "min": -0.11032278090715408,
+            "max": 0.295678973197937,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1685.9776611328125,
-            "min": 82.43424224853516,
-            "max": 1685.9776611328125,
-            "count": 10
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 71.8824691772461,
+            "min": -26.477466583251953,
+            "max": 76.58085632324219,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 10
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.0013886155793443322,
+            "min": -0.0017076353542506695,
+            "max": 0.39094293117523193,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 10
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -0.35965144634246826,
+            "min": -0.4371546506881714,
+            "max": 94.21724700927734,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06772408748465572,
-            "min": 0.06324473189660257,
-            "max": 0.0722757178929825,
-            "count": 10
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06754765192384919,
+            "min": 0.06478568333886232,
+            "max": 0.07358575871208399,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.33862043742327863,
-            "min": 0.25456921600647653,
-            "max": 0.36137858946491247,
-            "count": 10
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9456671269338888,
+            "min": 0.480868295816425,
+            "max": 1.0548193030037651,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.26413684066604165,
-            "min": 0.1389135341730663,
-            "max": 0.271015069063972,
-            "count": 10
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.012538805685922161,
+            "min": 0.0004524768144623889,
+            "max": 0.012538805685922161,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 1.3206842033302082,
-            "min": 0.5556541366922652,
-            "max": 1.35507534531986,
-            "count": 10
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.17554327960291025,
+            "min": 0.005882198588011056,
+            "max": 0.17554327960291025,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.6464094511999996e-05,
-            "min": 1.6464094511999996e-05,
-            "max": 0.000283764005412,
-            "count": 10
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.5860688999142866e-06,
+            "min": 7.5860688999142866e-06,
+            "max": 0.0002952361730165143,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 8.232047255999999e-05,
-            "min": 8.232047255999999e-05,
-            "max": 0.00127032007656,
-            "count": 10
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0001062049645988,
+            "min": 0.0001062049645988,
+            "max": 0.0033822119725960996,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.105488,
-            "min": 0.105488,
-            "max": 0.194588,
-            "count": 10
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10252865714285715,
+            "min": 0.10252865714285715,
+            "max": 0.19841205714285715,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.52744,
-            "min": 0.4615520000000001,
-            "max": 0.92344,
-            "count": 10
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4354012,
+            "min": 1.3888844,
+            "max": 2.5274039000000004,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0002838512,
-            "min": 0.0002838512,
-            "max": 0.0047299412,
-            "count": 10
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026261284857142863,
+            "min": 0.00026261284857142863,
+            "max": 0.009841364508571428,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.001419256,
-            "min": 0.001419256,
-            "max": 0.021179656,
-            "count": 10
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003676579880000001,
+            "min": 0.003676579880000001,
+            "max": 0.11276764961,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 17.672727272727272,
-            "min": 3.6818181818181817,
-            "max": 17.672727272727272,
-            "count": 10
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.015340897254645824,
+            "min": 0.015158257447183132,
+            "max": 0.6246576309204102,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 972.0,
-            "min": 162.0,
-            "max": 972.0,
-            "count": 10
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.214772567152977,
+            "min": 0.2122156023979187,
+            "max": 4.372603416442871,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 17.672727272727272,
-            "min": 3.6818181818181817,
-            "max": 17.672727272727272,
-            "count": 10
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 527.457627118644,
+            "min": 527.457627118644,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 972.0,
-            "min": 162.0,
-            "max": 972.0,
-            "count": 10
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31120.0,
+            "min": 16675.0,
+            "max": 33764.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.1703016634209682,
+            "min": -1.0000000521540642,
+            "max": 1.1703016634209682,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 69.04779814183712,
+            "min": -32.000001668930054,
+            "max": 69.04779814183712,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.1703016634209682,
+            "min": -1.0000000521540642,
+            "max": 1.1703016634209682,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 69.04779814183712,
+            "min": -32.000001668930054,
+            "max": 69.04779814183712,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.08352777892151468,
+            "min": 0.08352777892151468,
+            "max": 12.897804009563783,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 4.9281389563693665,
+            "min": 4.471724841743708,
+            "max": 219.2626681625843,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 33
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683117003",
+        "start_time_seconds": "1683117636",
         "python_version": "3.10.11 (main, Apr  5 2023, 14:15:10) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1683117249"
+        "end_time_seconds": "1683119745"
     },
-    "total": 246.8081528,
+    "total": 2109.166025959,
     "count": 1,
-    "self": 0.7884301389999848,
+    "self": 0.8892989739997574,
     "children": {
         "run_training.setup": {
-            "total": 0.03995504200000255,
+            "total": 0.04589672600002359,
             "count": 1,
-            "self": 0.03995504200000255
+            "self": 0.04589672600002359
         },
         "TrainerController.start_learning": {
-            "total": 245.979767619,
+            "total": 2108.230830259,
             "count": 1,
-            "self": 0.3581058350022772,
+            "self": 1.6261907840053027,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.298969027000027,
+                    "total": 3.885810552999942,
                     "count": 1,
-                    "self": 5.298969027000027
+                    "self": 3.885810552999942
                 },
                 "TrainerController.advance": {
-                    "total": 240.0946731209977,
-                    "count": 9139,
-                    "self": 0.1501838449973718,
+                    "total": 2102.575042304995,
+                    "count": 63340,
+                    "self": 1.5350413809892416,
                     "children": {
                         "env_step": {
-                            "total": 239.94448927600033,
-                            "count": 9139,
-                            "self": 175.41678418400514,
+                            "total": 1467.849041044005,
+                            "count": 63340,
+                            "self": 1351.0322012389936,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 64.37635004699823,
-                                    "count": 9139,
-                                    "self": 0.8765458759994829,
+                                    "total": 115.92192970497524,
+                                    "count": 63340,
+                                    "self": 4.876847897958214,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 63.49980417099874,
-                                            "count": 9139,
-                                            "self": 63.49980417099874
+                                            "total": 111.04508180701703,
+                                            "count": 62571,
+                                            "self": 111.04508180701703
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.1513550449969614,
-                                    "count": 9139,
+                                    "total": 0.8949101000360997,
+                                    "count": 63340,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 245.02767225000224,
-                                            "count": 9139,
+                                            "total": 2103.3071255419727,
+                                            "count": 63340,
                                             "is_parallel": true,
-                                            "self": 114.9387168160033,
+                                            "self": 868.1651775269902,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007437401000004229,
+                                                            "total": 0.0015664500000411863,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00547502000000577,
+                                                            "self": 0.0004160910000337026,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0019623809999984587,
-                                                                    "count": 10,
+                                                                    "total": 0.0011503590000074837,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0019623809999984587
+                                                                    "self": 0.0011503590000074837
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0344401019999907,
+                                                            "total": 0.07389690299999074,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005832839999868611,
+                                                            "self": 0.0005345690001377079,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003274489999967045,
+                                                                    "total": 0.0004652220000025409,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003274489999967045
+                                                                    "self": 0.0004652220000025409
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.031614434000005076,
+                                                                    "total": 0.07126625799992325,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.031614434000005076
+                                                                    "self": 0.07126625799992325
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019149350000020604,
+                                                                    "total": 0.0016308539999272398,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040229100011401897,
+                                                                    "self": 0.00035983199984457315,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015126439998880414,
-                                                                            "count": 10,
+                                                                            "total": 0.0012710220000826666,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015126439998880414
+                                                                            "self": 0.0012710220000826666
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 130.08895543399893,
-                                                    "count": 9138,
+                                                    "total": 1235.1419480149825,
+                                                    "count": 63339,
                                                     "is_parallel": true,
-                                                    "self": 5.163457792996184,
+                                                    "self": 31.906596027058185,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.731939688002228,
-                                                            "count": 9138,
+                                                            "total": 22.5041934649488,
+                                                            "count": 63339,
                                                             "is_parallel": true,
-                                                            "self": 2.731939688002228
+                                                            "self": 22.5041934649488
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 104.90102576300058,
-                                                            "count": 9138,
+                                                            "total": 1083.3254884010262,
+                                                            "count": 63339,
                                                             "is_parallel": true,
-                                                            "self": 104.90102576300058
+                                                            "self": 1083.3254884010262
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 17.292532189999946,
-                                                            "count": 9138,
+                                                            "total": 97.40567012194913,
+                                                            "count": 63339,
                                                             "is_parallel": true,
-                                                            "self": 3.356284920000519,
+                                                            "self": 20.291918079078187,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 13.936247269999427,
-                                                                    "count": 91380,
+                                                                    "total": 77.11375204287094,
+                                                                    "count": 506712,
                                                                     "is_parallel": true,
-                                                                    "self": 13.936247269999427
+                                                                    "self": 77.11375204287094
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00034299800000781033,
-                    "count": 1,
-                    "self": 0.00034299800000781033,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 633.1909598800007,
+                            "count": 63340,
+                            "self": 2.7233101200291685,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 238.38779213199737,
-                                    "count": 216031,
-                                    "is_parallel": true,
-                                    "self": 4.960322920997271,
+                                "process_trajectory": {
+                                    "total": 104.95484383497399,
+                                    "count": 63340,
+                                    "self": 104.63889837997397,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 131.30731688700004,
-                                            "count": 216031,
-                                            "is_parallel": true,
-                                            "self": 130.36027705900003,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.9470398280000154,
-                                                    "count": 2,
-                                                    "is_parallel": true,
-                                                    "self": 0.9470398280000154
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 102.12015232400006,
-                                            "count": 45,
-                                            "is_parallel": true,
-                                            "self": 37.010234576002745,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 65.10991774799732,
-                                                    "count": 2289,
-                                                    "is_parallel": true,
-                                                    "self": 65.10991774799732
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.31594545500001914,
+                                            "count": 2,
+                                            "self": 0.31594545500001914
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 525.5128059249976,
+                                    "count": 444,
+                                    "self": 338.5455011309914,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 186.96730479400617,
+                                            "count": 22830,
+                                            "self": 186.96730479400617
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.2269997569092084e-06,
+                    "count": 1,
+                    "self": 1.2269997569092084e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.22767663799999127,
+                    "total": 0.14378539000017554,
                     "count": 1,
-                    "self": 0.0012152099999980237,
+                    "self": 0.0019694910001817334,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.22646142799999325,
+                            "total": 0.1418158989999938,
                             "count": 1,
-                            "self": 0.22646142799999325
+                            "self": 0.1418158989999938
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,41 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.363636363636363,
-                "creation_time": 1683117127.122271,
+                "steps": 499909,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499909.onnx",
+                "reward": -0.9999000541865826,
+                "creation_time": 1683118622.4581826,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499909.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 18.818181818181817,
-                "creation_time": 1683117248.7362924,
+                "steps": 999920,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999920.onnx",
+                "reward": 1.5103333095709484,
+                "creation_time": 1683119744.8693933,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999920.pt"
                 ]
             },
             {
-                "steps": 100408,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.onnx",
-                "reward": 18.818181818181817,
-                "creation_time": 1683117249.0554194,
+                "steps": 1000048,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000048.onnx",
+                "reward": 1.5103333095709484,
+                "creation_time": 1683119745.0286217,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 100408,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 18.818181818181817,
-            "creation_time": 1683117249.0554194,
+            "steps": 1000048,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.5103333095709484,
+            "creation_time": 1683119745.0286217,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
             ]
         }
     },