Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5719525f09a1745ed3ffcd06976df8bcbfd26ce49801f59fe3b166dd2b66053
+oid sha256:07a8aee7bea4177abd67360cc2322e693c97f0b80e679d0251d8e0f95e9cf182
 size 2271327

Huggy/{Huggy-1199949.onnx → Huggy-1199994.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4665639927b69519ab92cd1dcba99bb888e1b0611d820a48ba76770b9ebfcb0
+oid sha256:d7d135a3070f9e260c5c562ea1312b0f33f1cd96e056036cfc4a76fea7449ba8
 size 2271327

Huggy/{Huggy-1799985.pt → Huggy-1199994.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e85d1f1c9f6d53c41ec31eb66e70b7147b206a3e26e0991e5fe1918c058cca0
+oid sha256:4ef9c92e7e25e4771a09bf6e0cdc856264b92ef3df9c0a4a2b8585497a3cec6c
 size 13503717

Huggy/{Huggy-1799985.onnx → Huggy-1399956.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49297ccd4d376287227012f33e9bb3ff39b78526030160968da7b7885fcb9e94
+oid sha256:14de3deb0ae74b0f3c86c7db288cbc9636cf576bb981c3ce68f090f66756e1e8
 size 2271327

Huggy/{Huggy-1199949.pt → Huggy-1399956.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2225433f63f0d5694ee46666fa5bfb4f42e92c51ed51c0964632cd6f384f0cc
+oid sha256:9d047c20c596cb9a8ab2bc536b1077817a13d28fa63f614fa9dcdaca3e503d46
 size 13503717

Huggy/{Huggy-1499868.onnx → Huggy-1599908.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77dec0da834bbb1ae257a2128ce0feef28123fcffb22d6c524b11fcd4b3f452
+oid sha256:fcb6c764f3f19794dfd1e463567eb96c976784aed1728f454de258de91e4ba33
 size 2271327

Huggy/{Huggy-2000073.pt → Huggy-1599908.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4baf6105af78b13e52400d408d561fe109e7640851c1f2ec16500b773313a2f
+oid sha256:5695a5f84027096091682229391cfa5ebfad0642080af90a711b6e408c4d39bd
 size 13503717

Huggy/{Huggy-2000073.onnx → Huggy-1799936.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5719525f09a1745ed3ffcd06976df8bcbfd26ce49801f59fe3b166dd2b66053
+oid sha256:cd6da60621b1e8f82e44e3a0ced882a8cc0811a4abbcc930f6af5506d5229fb0
 size 2271327

Huggy/{Huggy-1499868.pt → Huggy-1799936.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be1db1d180a67c1bc62e5bb39b2b3aa95118a4212021ec95c63f208c21d2e99
+oid sha256:cc1fc13395634bec7e55d1075fbe680c93555ac621c360b405a6145aa0d58a63
 size 13503717

Huggy/Huggy-199673.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949319a37df1e820c79b0a6890eb331c46dbffa7ad91ffbf34196b7e50ee2598
+size 2271327

Huggy/Huggy-199673.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6484f9c4064465d28581a09b5647cc25a96a9bd8c937248e0baaae39690cc5a6
+size 13503717

Huggy/Huggy-1999967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78d0d0796e09a4088098b096566da3d8c03f31e7430e08e82b411f4e01ef6a8
+size 2271327

Huggy/Huggy-1999967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2250ee1a85ecac43cb1ac9a7c8c1d99bf9865b03e89bf37101003dba6c90e1dd
+size 13503717

Huggy/Huggy-2000065.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a8aee7bea4177abd67360cc2322e693c97f0b80e679d0251d8e0f95e9cf182
+size 2271327

Huggy/Huggy-2000065.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287e3612f34446cc71d9628347fd3c75d65a2687b196a9c29195e69ac9e0eeb5
+size 13503717

Huggy/Huggy-299871.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5302f1bf452d8384f728576d387a65f0968e57a03d95bfa537a2439e14bc7c3a
-size 2271327

Huggy/Huggy-299871.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b9b859528d10421a5e562ec3d9f724b7436eed423a7b16f41892c6337a6231c
-size 13503717

Huggy/Huggy-399908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b1398481e37b4ba944791085a02e9f1e89db968b9267b863a7838c728c76f3
+size 2271327

Huggy/Huggy-399908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef2a8597335e2335f9d1ced85f48bd7093acd4f890ec812a7137aaf0843d153
+size 13503717

Huggy/Huggy-599901.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9745cd9458ccab66dce8bb5ea7b33f1da6e1d8cc8397db8d07c44e8e4e1e34ad
+size 2271327

Huggy/Huggy-599901.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839351fff6b0ea12c66ae967ea730bae0868bb014818e2d83cc9e17071258fac
+size 13503717

Huggy/Huggy-599907.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2544d1a9d40945fc97752b163543c0c799f0f8261da1d40af8428b515ff296f8
-size 2271327

Huggy/Huggy-599907.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:920218dfa483d78362b7936dc8ae248b90c6cb369dcb427771d79ffb2fd2af83
-size 13503717

Huggy/Huggy-799954.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3d51a8b66de3e4a6a444b9d08e8f69d01c7e5086eadb2ec4e72f26e63b8f12
+size 2271327

Huggy/Huggy-799954.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bed4b5963f89f76934dcb683e05869a93c368701d47f39c475158ec57624513
+size 13503717

Huggy/Huggy-899922.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2948ada7a8a28ef32530c00a0a744832cceab74e39456caf92d5553cd4a874c
-size 2271327

Huggy/Huggy-899922.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:faa30d3e9b9b5df16adc3e45db5e71be27f2b60ff89a6e8e55545aad3b860517
-size 13503717

Huggy/Huggy-999980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaf1debf84aec1519e4ac5c0d1fc344db0b3d6d910c43915fb5b1c44308deb9
+size 2271327

Huggy/Huggy-999980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8bea7929b89bd5d1bc9681a421fd7f942d6d58b0a812a5ad12f72217c5b5e6
+size 13503717

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4baf6105af78b13e52400d408d561fe109e7640851c1f2ec16500b773313a2f
+oid sha256:287e3612f34446cc71d9628347fd3c75d65a2687b196a9c29195e69ac9e0eeb5
 size 13503717

Huggy/{events.out.tfevents.1681290054.51e1946f3b41.1398.0 → events.out.tfevents.1681294082.af0af7789269.3218.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60fde53d6b5114afa89aef67392a41d52c58163bb6c71f4fcda40d66b4ad8df7
-size 388017
+oid sha256:cf32add3c72b5ed35e331822943c9f00f1739674d64a852df54813884d211421
+size 314529

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 6, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 300000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "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": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.008, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "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

@@ -6,15 +6,15 @@ behaviors:
       batch_size: 2048
       buffer_size: 20480
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.008
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 6
+      num_epoch: 5
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 300000
+    checkpoint_interval: 200000
     network_settings:
       normalize: true
       hidden_units: 512

run_logs/Player-0.log

@@ -34,7 +34,7 @@ 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  0.085 seconds
+- Completed reload, in  0.133 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +78,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - 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: 0.930254 ms
+UnloadTime: 1.029281 ms
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26759 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26764 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -93,7 +93,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 160 B
+      Peak Allocated Bytes 128 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -207,16 +207,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26760 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.4 MB
+      Peak Allocated memory 23.5 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26760 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 26765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.6 MB
+      Peak Allocated memory 2.8 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -245,13 +245,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26759 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26764 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26760 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +263,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26759 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26764 frames, [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 24.9 MB
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 26759 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26764 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -281,13 +281,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26760 frames
+      Peak usage frame count: [0-1.0 KB]: 26765 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: [4.0 KB-8.0 KB]: 26760 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26765 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,135 +2,135 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.3345599174499512,
-            "min": 1.3345599174499512,
-            "max": 1.4183331727981567,
+            "value": 1.3912911415100098,
+            "min": 1.3912911415100098,
+            "max": 1.4321794509887695,
             "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 67881.0546875,
-            "min": 65428.234375,
-            "max": 75028.40625,
+            "value": 69954.1171875,
+            "min": 67970.546875,
+            "max": 79457.46875,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 89.38086642599278,
-            "min": 80.77152317880795,
-            "max": 412.6694214876033,
+            "value": 100.1417004048583,
+            "min": 81.13628899835797,
+            "max": 385.60769230769233,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49517.0,
-            "min": 48786.0,
-            "max": 50031.0,
+            "value": 49470.0,
+            "min": 48960.0,
+            "max": 50137.0,
             "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 1999946.0,
-            "min": 49405.0,
-            "max": 1999946.0,
+            "value": 1999967.0,
+            "min": 49883.0,
+            "max": 1999967.0,
             "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 1999946.0,
-            "min": 49405.0,
-            "max": 1999946.0,
+            "value": 1999967.0,
+            "min": 49883.0,
+            "max": 1999967.0,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.3557186126708984,
-            "min": 0.06346326321363449,
-            "max": 2.4251322746276855,
+            "value": 2.3654301166534424,
+            "min": 0.05287821590900421,
+            "max": 2.4686388969421387,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1305.068115234375,
-            "min": 7.615592002868652,
-            "max": 1433.103515625,
+            "value": 1168.5224609375,
+            "min": 6.821290016174316,
+            "max": 1470.3707275390625,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.6441511756031093,
-            "min": 1.837630920857191,
-            "max": 3.9443035696943602,
+            "value": 3.565265215239544,
+            "min": 1.860402266184489,
+            "max": 4.010823725296316,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 2018.8597512841225,
-            "min": 220.51571050286293,
-            "max": 2270.714448392391,
+            "value": 1761.2410163283348,
+            "min": 239.99189233779907,
+            "max": 2313.483722150326,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.6441511756031093,
-            "min": 1.837630920857191,
-            "max": 3.9443035696943602,
+            "value": 3.565265215239544,
+            "min": 1.860402266184489,
+            "max": 4.010823725296316,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 2018.8597512841225,
-            "min": 220.51571050286293,
-            "max": 2270.714448392391,
+            "value": 1761.2410163283348,
+            "min": 239.99189233779907,
+            "max": 2313.483722150326,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.01572396343257828,
-            "min": 0.015516515240839605,
-            "max": 0.020166200002697424,
+            "value": 0.01907226402099089,
+            "min": 0.014840562724906097,
+            "max": 0.01943226710349942,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.04717189029773484,
-            "min": 0.03103303048167921,
-            "max": 0.060498600008092276,
+            "value": 0.05721679206297267,
+            "min": 0.02975640016491525,
+            "max": 0.05829680131049826,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.049407594982120724,
-            "min": 0.018967929653202494,
-            "max": 0.049407594982120724,
+            "value": 0.04438812963664531,
+            "min": 0.02004504397511482,
+            "max": 0.04870500929653645,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.14822278494636218,
-            "min": 0.03793585930640499,
-            "max": 0.14822278494636218,
+            "value": 0.13316438890993593,
+            "min": 0.04009008795022964,
+            "max": 0.14611502788960934,
             "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.4561988479666626e-06,
-            "min": 3.4561988479666626e-06,
-            "max": 0.000295314976561675,
+            "value": 3.3528488824166707e-06,
+            "min": 3.3528488824166707e-06,
+            "max": 0.00029534475155175,
             "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 1.0368596543899988e-05,
-            "min": 1.0368596543899988e-05,
-            "max": 0.0008440773186409,
+            "value": 1.0058546647250013e-05,
+            "min": 1.0058546647250013e-05,
+            "max": 0.00084399826866725,
             "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10115203333333332,
-            "min": 0.10115203333333332,
-            "max": 0.19843832499999997,
+            "value": 0.10111758333333333,
+            "min": 0.10111758333333333,
+            "max": 0.19844825000000002,
             "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30345609999999995,
-            "min": 0.2075103500000001,
-            "max": 0.5813591,
+            "value": 0.30335275,
+            "min": 0.20738060000000003,
+            "max": 0.58133275,
             "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 6.748646333333326e-05,
-            "min": 6.748646333333326e-05,
-            "max": 0.004922072417500001,
+            "value": 9.929490833333345e-05,
+            "min": 9.929490833333345e-05,
+            "max": 0.007876015175,
             "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.0002024593899999998,
-            "min": 0.0002024593899999998,
-            "max": 0.014069819090000001,
+            "value": 0.00029788472500000035,
+            "min": 0.00029788472500000035,
+            "max": 0.022508486725000002,
             "count": 40
         },
         "Huggy.IsTraining.mean": {
@@ -148,7 +148,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1681290053",
+        "start_time_seconds": "1681294081",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
         "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1681292825"
+        "end_time_seconds": "1681296631"
     },
-    "total": 2771.914535918,
+    "total": 2549.7273095339997,
     "count": 1,
-    "self": 0.449943897000594,
+    "self": 0.3865502660000857,
     "children": {
         "run_training.setup": {
-            "total": 0.1119188469999699,
+            "total": 0.11098535099995388,
             "count": 1,
-            "self": 0.1119188469999699
+            "self": 0.11098535099995388
         },
         "TrainerController.start_learning": {
-            "total": 2771.352673174,
+            "total": 2549.229773917,
             "count": 1,
-            "self": 4.249151965969304,
+            "self": 4.171735840070141,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.9517179279999937,
+                    "total": 5.14989561699997,
                     "count": 1,
-                    "self": 3.9517179279999937
+                    "self": 5.14989561699997
                 },
                 "TrainerController.advance": {
-                    "total": 2763.0311802510305,
-                    "count": 232407,
-                    "self": 4.658842670139165,
+                    "total": 2539.78551325793,
+                    "count": 232427,
+                    "self": 4.7203178089721405,
                     "children": {
                         "env_step": {
-                            "total": 1862.3607647929189,
-                            "count": 232407,
-                            "self": 1577.6232689629333,
+                            "total": 1796.1700640990111,
+                            "count": 232427,
+                            "self": 1523.817247328158,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 281.82264681200957,
-                                    "count": 232407,
-                                    "self": 16.93567151002145,
+                                    "total": 269.64230912088124,
+                                    "count": 232427,
+                                    "self": 15.973916661902308,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 264.8869753019881,
-                                            "count": 222998,
-                                            "self": 264.8869753019881
+                                            "total": 253.66839245897893,
+                                            "count": 223036,
+                                            "self": 253.66839245897893
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.9148490179761097,
-                                    "count": 232407,
+                                    "total": 2.710507649972101,
+                                    "count": 232427,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2763.3663964869093,
-                                            "count": 232407,
+                                            "total": 2541.1920941309254,
+                                            "count": 232427,
                                             "is_parallel": true,
-                                            "self": 1471.729047247889,
+                                            "self": 1289.446742319943,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009125390000122025,
+                                                            "total": 0.001186763999953655,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00022585200002822603,
+                                                            "self": 0.00028692799992313667,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006866869999839764,
+                                                                    "total": 0.0008998360000305183,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006866869999839764
+                                                                    "self": 0.0008998360000305183
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.028268859999968754,
+                                                            "total": 0.02954485400005069,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003542469999047171,
+                                                            "self": 0.00032299600024998654,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002364630000215584,
+                                                                    "total": 0.00021970899990719772,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002364630000215584
+                                                                    "self": 0.00021970899990719772
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.026935682000043926,
+                                                                    "total": 0.02833385399992494,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.026935682000043926
+                                                                    "self": 0.02833385399992494
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007424679999985528,
+                                                                    "total": 0.0006682949999685661,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00021920799997587892,
+                                                                    "self": 0.00020264800002678385,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005232600000226739,
+                                                                            "total": 0.00046564699994178227,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005232600000226739
+                                                                            "self": 0.00046564699994178227
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1291.6373492390203,
-                                                    "count": 232406,
+                                                    "total": 1251.7453518109824,
+                                                    "count": 232426,
                                                     "is_parallel": true,
-                                                    "self": 38.97164069903761,
+                                                    "self": 38.1061419089674,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 81.17128163794183,
-                                                            "count": 232406,
+                                                            "total": 79.41699104193435,
+                                                            "count": 232426,
                                                             "is_parallel": true,
-                                                            "self": 81.17128163794183
+                                                            "self": 79.41699104193435
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1080.0861587190332,
-                                                            "count": 232406,
+                                                            "total": 1045.96751277998,
+                                                            "count": 232426,
                                                             "is_parallel": true,
-                                                            "self": 1080.0861587190332
+                                                            "self": 1045.96751277998
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 91.40826818300769,
-                                                            "count": 232406,
+                                                            "total": 88.25470608010039,
+                                                            "count": 232426,
                                                             "is_parallel": true,
-                                                            "self": 34.71495096496011,
+                                                            "self": 32.859660275050715,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 56.69331721804758,
-                                                                    "count": 464812,
+                                                                    "total": 55.395045805049676,
+                                                                    "count": 464852,
                                                                     "is_parallel": true,
-                                                                    "self": 56.69331721804758
+                                                                    "self": 55.395045805049676
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 896.0115727879725,
-                            "count": 232407,
-                            "self": 6.50386953691941,
+                            "total": 738.8951313499467,
+                            "count": 232427,
+                            "self": 6.3756344480611915,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 133.65490201705273,
-                                    "count": 232407,
-                                    "self": 132.7949492200524,
+                                    "total": 128.16352188288693,
+                                    "count": 232427,
+                                    "self": 126.89712775988608,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.8599527970003464,
-                                            "count": 6,
-                                            "self": 0.8599527970003464
+                                            "total": 1.2663941230008504,
+                                            "count": 10,
+                                            "self": 1.2663941230008504
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 755.8528012340003,
+                                    "total": 604.3559750189986,
                                     "count": 97,
-                                    "self": 635.4611914520026,
+                                    "self": 507.3259088749925,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 120.39160978199772,
-                                            "count": 5820,
-                                            "self": 120.39160978199772
+                                            "total": 97.03006614400613,
+                                            "count": 4850,
+                                            "self": 97.03006614400613
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.930001058615744e-07,
+                    "total": 1.297999915550463e-06,
                     "count": 1,
-                    "self": 8.930001058615744e-07
+                    "self": 1.297999915550463e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12062213599983806,
+                    "total": 0.12262790400018275,
                     "count": 1,
-                    "self": 0.0020701099997495476,
+                    "self": 0.0020049560002917133,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11855202600008852,
+                            "total": 0.12062294799989104,
                             "count": 1,
-                            "self": 0.11855202600008852
+                            "self": 0.12062294799989104
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,76 +2,112 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 299871,
-                "file_path": "results/Huggy/Huggy/Huggy-299871.onnx",
-                "reward": 3.770768107686724,
-                "creation_time": 1681290466.354844,
+                "steps": 199673,
+                "file_path": "results/Huggy/Huggy/Huggy-199673.onnx",
+                "reward": 3.4741778338133398,
+                "creation_time": 1681294335.9804747,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-299871.pt"
+                    "results/Huggy/Huggy/Huggy-199673.pt"
                 ]
             },
             {
-                "steps": 599907,
-                "file_path": "results/Huggy/Huggy/Huggy-599907.onnx",
-                "reward": 3.6540495936687174,
-                "creation_time": 1681290889.676333,
+                "steps": 399908,
+                "file_path": "results/Huggy/Huggy/Huggy-399908.onnx",
+                "reward": 3.599922402865357,
+                "creation_time": 1681294592.82653,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599907.pt"
+                    "results/Huggy/Huggy/Huggy-399908.pt"
                 ]
             },
             {
-                "steps": 899922,
-                "file_path": "results/Huggy/Huggy/Huggy-899922.onnx",
-                "reward": 3.9759086707704947,
-                "creation_time": 1681291303.7819135,
+                "steps": 599901,
+                "file_path": "results/Huggy/Huggy/Huggy-599901.onnx",
+                "reward": 4.320858573212343,
+                "creation_time": 1681294852.6186972,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-899922.pt"
+                    "results/Huggy/Huggy/Huggy-599901.pt"
                 ]
             },
             {
-                "steps": 1199949,
-                "file_path": "results/Huggy/Huggy/Huggy-1199949.onnx",
-                "reward": 3.9082083237635623,
-                "creation_time": 1681291726.6017601,
+                "steps": 799954,
+                "file_path": "results/Huggy/Huggy/Huggy-799954.onnx",
+                "reward": 3.914150916260375,
+                "creation_time": 1681295104.7471213,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1199949.pt"
+                    "results/Huggy/Huggy/Huggy-799954.pt"
                 ]
             },
             {
-                "steps": 1499868,
-                "file_path": "results/Huggy/Huggy/Huggy-1499868.onnx",
-                "reward": 3.7710096386895664,
-                "creation_time": 1681292129.198801,
+                "steps": 999980,
+                "file_path": "results/Huggy/Huggy/Huggy-999980.onnx",
+                "reward": 3.650248147840575,
+                "creation_time": 1681295362.2802663,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1499868.pt"
+                    "results/Huggy/Huggy/Huggy-999980.pt"
                 ]
             },
             {
-                "steps": 1799985,
-                "file_path": "results/Huggy/Huggy/Huggy-1799985.onnx",
-                "reward": 3.5940499126911165,
-                "creation_time": 1681292546.3404148,
+                "steps": 1199994,
+                "file_path": "results/Huggy/Huggy/Huggy-1199994.onnx",
+                "reward": 3.9295015771474158,
+                "creation_time": 1681295617.399696,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1799985.pt"
+                    "results/Huggy/Huggy/Huggy-1199994.pt"
                 ]
             },
             {
-                "steps": 2000073,
-                "file_path": "results/Huggy/Huggy/Huggy-2000073.onnx",
-                "reward": 3.9013504485289254,
-                "creation_time": 1681292825.3168359,
+                "steps": 1399956,
+                "file_path": "results/Huggy/Huggy/Huggy-1399956.onnx",
+                "reward": 3.7267734844447213,
+                "creation_time": 1681295867.3508618,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000073.pt"
+                    "results/Huggy/Huggy/Huggy-1399956.pt"
+                ]
+            },
+            {
+                "steps": 1599908,
+                "file_path": "results/Huggy/Huggy/Huggy-1599908.onnx",
+                "reward": 3.740986238826405,
+                "creation_time": 1681296122.2619357,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1599908.pt"
+                ]
+            },
+            {
+                "steps": 1799936,
+                "file_path": "results/Huggy/Huggy/Huggy-1799936.onnx",
+                "reward": 3.218651219492867,
+                "creation_time": 1681296375.8856835,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1799936.pt"
+                ]
+            },
+            {
+                "steps": 1999967,
+                "file_path": "results/Huggy/Huggy/Huggy-1999967.onnx",
+                "reward": 3.4565091451009113,
+                "creation_time": 1681296630.8104777,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1999967.pt"
+                ]
+            },
+            {
+                "steps": 2000065,
+                "file_path": "results/Huggy/Huggy/Huggy-2000065.onnx",
+                "reward": 3.6479759216308594,
+                "creation_time": 1681296630.936439,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2000065.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000073,
+            "steps": 2000065,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.9013504485289254,
-            "creation_time": 1681292825.3168359,
+            "reward": 3.6479759216308594,
+            "creation_time": 1681296630.936439,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000073.pt"
+                "results/Huggy/Huggy/Huggy-2000065.pt"
             ]
         }
     },