Hugging Face's logo

pmolodo
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files Metrics Community
pmolodo commited on
Commit
0b32265
·
verified ·
1 Parent(s): a3abd8c

Huggy

Browse files
Files changed (12) hide show
  1. Huggy.onnx +1 -1
  2. Huggy/Huggy-1799960.onnx +3 -0
  3. Huggy/Huggy-1799960.pt +3 -0
  4. Huggy/Huggy-1999985.onnx +3 -0
  5. Huggy/Huggy-1999985.pt +3 -0
  6. Huggy/Huggy-2000037.onnx +3 -0
  7. Huggy/Huggy-2000037.pt +3 -0
  8. Huggy/checkpoint.pt +1 -1
  9. Huggy/events.out.tfevents.1715403133.45baf7a9ad02.15508.0 +3 -0
  10. run_logs/Player-0.log +13 -13
  11. run_logs/timers.json +167 -167
  12. run_logs/training_status.json +31 -22
Huggy.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d095079d000502a55cd81b816cedbfa118bbc07f6e70fe61dba3fcabfd3ea418
3
  size 2273984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234586ef41084eae86089372a412ea63de8666e2f1733c56fdc9cc09cc93888c
3
  size 2273984
Huggy/Huggy-1799960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66c389480ccab93a95d3713148be05200acc329cd342544fe21d14e2190112a
3
+ size 2273984
Huggy/Huggy-1799960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760838e65900c5866c6c5d56b00b52ad9f3365cab79d441c7197c5c74a7b7ae0
3
+ size 13509473
Huggy/Huggy-1999985.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894863938dd8011284e582e9498974d925a577989fc8cc1429cb290a8d910ea2
3
+ size 2273984
Huggy/Huggy-1999985.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc363fe83bc87f02d0ceeae7b274810024a88177df724eeec3402f70366bf29a
3
+ size 13509473
Huggy/Huggy-2000037.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234586ef41084eae86089372a412ea63de8666e2f1733c56fdc9cc09cc93888c
3
+ size 2273984
Huggy/Huggy-2000037.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66dea74d1874e1ad00898747e25501c02ed5524f0c442b722b5317aadfdba89c
3
+ size 13509473
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bad48351dfe1e939d9b3eb8d5758f50f29b67e54d468a20807c97b8c07719d9
3
  size 13509218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810aab9864f5b6d849944cbc861c4c74d51f0d268671b5717770a408c2c3af4f
3
  size 13509218
Huggy/events.out.tfevents.1715403133.45baf7a9ad02.15508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44c9bb11521ac973806a4a7c8dd9b970485375e4c639fda3a31540a3d1009de
3
+ size 37377
run_logs/Player-0.log CHANGED
@@ -75,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
- UnloadTime: 0.822616 ms
79
  requesting resize 84 x 84
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
- Peak usage frame count: [4.0 KB-8.0 KB]: 9249 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
@@ -90,7 +90,7 @@ Memory Statistics:
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
- Peak Allocated Bytes 256 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
@@ -198,22 +198,22 @@ Memory Statistics:
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
- Peak main deferred allocation count 307
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
- Peak usage frame count: [16.0 MB-32.0 MB]: 9250 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
  Peak Allocated memory 22.4 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
- Peak usage frame count: [2.0 MB-4.0 MB]: 9250 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 2.6 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
@@ -242,13 +242,13 @@ Memory Statistics:
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
- Peak usage frame count: [32.0 KB-64.0 KB]: 9249 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
- Peak usage frame count: [64.0 KB-128.0 KB]: 9250 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
@@ -260,13 +260,13 @@ Memory Statistics:
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
- Peak usage frame count: [1.0 MB-2.0 MB]: 9249 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
- Peak usage frame count: [0.5 MB-1.0 MB]: 9249 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
@@ -278,13 +278,13 @@ Memory Statistics:
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
- Peak usage frame count: [0-1.0 KB]: 9250 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
- Peak usage frame count: [4.0 KB-8.0 KB]: 9250 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  Peak Allocated memory 7.3 KB
 
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
+ UnloadTime: 1.015187 ms
79
  requesting resize 84 x 84
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
+ Peak usage frame count: [4.0 KB-8.0 KB]: 4160 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
 
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
+ Peak Allocated Bytes 136 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
 
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
+ Peak main deferred allocation count 250
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
+ Peak usage frame count: [16.0 MB-32.0 MB]: 4161 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
  Peak Allocated memory 22.4 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [2.0 MB-4.0 MB]: 4161 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 2.4 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
 
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4160 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
+ Peak usage frame count: [64.0 KB-128.0 KB]: 4161 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
 
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
+ Peak usage frame count: [1.0 MB-2.0 MB]: 4160 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
+ Peak usage frame count: [0.5 MB-1.0 MB]: 4160 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
 
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
+ Peak usage frame count: [0-1.0 KB]: 4161 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
+ Peak usage frame count: [4.0 KB-8.0 KB]: 4161 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  Peak Allocated memory 7.3 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
- "value": 1.4101125001907349,
6
- "min": 1.4101125001907349,
7
- "max": 1.4179699420928955,
8
- "count": 14
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
- "value": 72338.7734375,
12
- "min": 711.8209228515625,
13
- "max": 72338.7734375,
14
- "count": 14
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
- "value": 85.88020833333333,
18
- "min": 18.75,
19
- "max": 91.0865561694291,
20
- "count": 14
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
- "value": 49467.0,
24
- "min": 75.0,
25
- "max": 49644.0,
26
- "count": 14
27
  },
28
  "Huggy.Step.mean": {
29
- "value": 1649993.0,
30
- "min": 999973.0,
31
- "max": 1649993.0,
32
- "count": 14
33
  },
34
  "Huggy.Step.sum": {
35
- "value": 1649993.0,
36
- "min": 999973.0,
37
- "max": 1649993.0,
38
- "count": 14
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 2.45137619972229,
42
- "min": 1.314420223236084,
43
- "max": 2.45137619972229,
44
- "count": 14
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 1411.99267578125,
48
- "min": 3.943260669708252,
49
- "max": 1452.5228271484375,
50
- "count": 14
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
- "value": 3.864656989566154,
54
- "min": 1.5244582096735637,
55
- "max": 3.9523238473351348,
56
- "count": 14
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
- "value": 2226.0424259901047,
60
- "min": 4.573374629020691,
61
- "max": 2319.6946780085564,
62
- "count": 14
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
- "value": 3.864656989566154,
66
- "min": 1.5244582096735637,
67
- "max": 3.9523238473351348,
68
- "count": 14
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
- "value": 2226.0424259901047,
72
- "min": 4.573374629020691,
73
- "max": 2319.6946780085564,
74
- "count": 14
75
  },
76
  "Huggy.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
- "count": 14
81
  },
82
  "Huggy.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
- "count": 14
87
  },
88
  "Huggy.Losses.PolicyLoss.mean": {
89
- "value": 0.01870435419356606,
90
- "min": 0.01476140577190866,
91
- "max": 0.01942255970779014,
92
- "count": 13
93
  },
94
  "Huggy.Losses.PolicyLoss.sum": {
95
- "value": 0.03740870838713212,
96
- "min": 0.02952281154381732,
97
- "max": 0.05826767912337042,
98
- "count": 13
99
  },
100
  "Huggy.Losses.ValueLoss.mean": {
101
- "value": 0.04889580296973388,
102
- "min": 0.04889580296973388,
103
- "max": 0.05568473419795433,
104
- "count": 13
105
  },
106
  "Huggy.Losses.ValueLoss.sum": {
107
- "value": 0.09779160593946776,
108
- "min": 0.09779160593946776,
109
- "max": 0.16295202188193797,
110
- "count": 13
111
  },
112
  "Huggy.Policy.LearningRate.mean": {
113
- "value": 5.584245638587501e-05,
114
- "min": 5.584245638587501e-05,
115
- "max": 0.00014539767653412504,
116
- "count": 13
117
  },
118
  "Huggy.Policy.LearningRate.sum": {
119
- "value": 0.00011168491277175003,
120
- "min": 0.00011168491277175003,
121
- "max": 0.00039461821846064997,
122
- "count": 13
123
  },
124
  "Huggy.Policy.Epsilon.mean": {
125
- "value": 0.11861412500000003,
126
- "min": 0.11861412500000003,
127
- "max": 0.14846587500000002,
128
- "count": 13
129
  },
130
  "Huggy.Policy.Epsilon.sum": {
131
- "value": 0.23722825000000006,
132
- "min": 0.23722825000000006,
133
- "max": 0.4315393500000001,
134
- "count": 13
135
  },
136
  "Huggy.Policy.Beta.mean": {
137
- "value": 0.0009388448375000004,
138
- "min": 0.0009388448375000004,
139
- "max": 0.0024284471625000002,
140
- "count": 13
141
  },
142
  "Huggy.Policy.Beta.sum": {
143
- "value": 0.0018776896750000009,
144
- "min": 0.0018776896750000009,
145
- "max": 0.006593813565,
146
- "count": 13
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1715402105",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1715403022"
160
  },
161
- "total": 917.516375191,
162
  "count": 1,
163
- "self": 0.5313059970003451,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05148377899968182,
167
  "count": 1,
168
- "self": 0.05148377899968182
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 916.9335854149999,
172
  "count": 1,
173
- "self": 1.7121398390572722,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.1524120710000716,
177
  "count": 1,
178
- "self": 2.1524120710000716
179
  },
180
  "TrainerController.advance": {
181
- "total": 912.7069062229425,
182
- "count": 80963,
183
- "self": 1.8373896899447573,
184
  "children": {
185
  "env_step": {
186
- "total": 725.5388859719801,
187
- "count": 80963,
188
- "self": 600.4469809209963,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 123.94342937005013,
192
- "count": 80963,
193
- "self": 6.141724788992178,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 117.80170458105795,
197
- "count": 77083,
198
- "self": 117.80170458105795
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 1.1484756809336432,
204
- "count": 80963,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 913.9311555420604,
209
- "count": 80963,
210
  "is_parallel": true,
211
- "self": 432.8517007100113,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.0009686220000730827,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0002913719999924069,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0006772500000806758,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.0006772500000806758
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.06247939000013503,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00039084800073396764,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00020346999963294365,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00020346999963294365
244
  },
245
  "communicator.exchange": {
246
- "total": 0.061119064999729744,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.061119064999729744
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0007660070000383712,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0001840019999690412,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.00058200500006933,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.00058200500006933
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 481.0794548320491,
271
- "count": 80962,
272
  "is_parallel": true,
273
- "self": 14.445195133951984,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 31.281643202011765,
277
- "count": 80962,
278
  "is_parallel": true,
279
- "self": 31.281643202011765
280
  },
281
  "communicator.exchange": {
282
- "total": 401.6391034669746,
283
- "count": 80962,
284
  "is_parallel": true,
285
- "self": 401.6391034669746
286
  },
287
  "steps_from_proto": {
288
- "total": 33.7135130291108,
289
- "count": 80962,
290
  "is_parallel": true,
291
- "self": 12.787688226063437,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 20.925824803047362,
295
- "count": 161924,
296
  "is_parallel": true,
297
- "self": 20.925824803047362
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 185.33063056101764,
311
- "count": 80963,
312
- "self": 2.5159893870195447,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 63.753239228999064,
316
- "count": 80963,
317
- "self": 63.088509670998974,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.66472955800009,
321
- "count": 4,
322
- "self": 0.66472955800009
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 119.06140194499903,
328
- "count": 33,
329
- "self": 96.41674164599954,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 22.644660298999497,
333
- "count": 990,
334
- "self": 22.644660298999497
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.2900000001536682e-06,
344
  "count": 1,
345
- "self": 1.2900000001536682e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.3621259920000739,
349
  "count": 1,
350
- "self": 0.005341598000086378,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.3567843939999875,
354
  "count": 1,
355
- "self": 0.3567843939999875
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4087876081466675,
6
+ "min": 1.4087876081466675,
7
+ "max": 1.4096214771270752,
8
+ "count": 7
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
+ "value": 69446.1875,
12
+ "min": 15487.51171875,
13
+ "max": 71457.890625,
14
+ "count": 7
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 78.60668789808918,
18
+ "min": 67.99312242090784,
19
+ "max": 78.60668789808918,
20
+ "count": 7
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49365.0,
24
+ "min": 10138.0,
25
+ "max": 49431.0,
26
+ "count": 7
27
  },
28
  "Huggy.Step.mean": {
29
+ "value": 1999985.0,
30
+ "min": 1699995.0,
31
+ "max": 1999985.0,
32
+ "count": 7
33
  },
34
  "Huggy.Step.sum": {
35
+ "value": 1999985.0,
36
+ "min": 1699995.0,
37
+ "max": 1999985.0,
38
+ "count": 7
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.519611358642578,
42
+ "min": 2.422769069671631,
43
+ "max": 2.519611358642578,
44
+ "count": 7
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1582.31591796875,
48
+ "min": 364.6850280761719,
49
+ "max": 1761.35302734375,
50
+ "count": 7
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 4.001143987201582,
54
+ "min": 3.8549074130504297,
55
+ "max": 4.0609446367850675,
56
+ "count": 7
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 2512.718423962593,
60
+ "min": 580.319584608078,
61
+ "max": 2802.5176892876625,
62
+ "count": 7
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 4.001143987201582,
66
+ "min": 3.8549074130504297,
67
+ "max": 4.0609446367850675,
68
+ "count": 7
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 2512.718423962593,
72
+ "min": 580.319584608078,
73
+ "max": 2802.5176892876625,
74
+ "count": 7
75
  },
76
  "Huggy.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
+ "count": 7
81
  },
82
  "Huggy.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
+ "count": 7
87
  },
88
  "Huggy.Losses.PolicyLoss.mean": {
89
+ "value": 0.016529316230702938,
90
+ "min": 0.015394263728133713,
91
+ "max": 0.018989399625570513,
92
+ "count": 6
93
  },
94
  "Huggy.Losses.PolicyLoss.sum": {
95
+ "value": 0.049587948692108814,
96
+ "min": 0.03086950963285441,
97
+ "max": 0.05031169712456176,
98
+ "count": 6
99
  },
100
  "Huggy.Losses.ValueLoss.mean": {
101
+ "value": 0.05982795287337569,
102
+ "min": 0.056809495699902374,
103
+ "max": 0.06415955157329639,
104
+ "count": 6
105
  },
106
  "Huggy.Losses.ValueLoss.sum": {
107
+ "value": 0.17948385862012706,
108
+ "min": 0.11361899139980475,
109
+ "max": 0.18040379596253237,
110
+ "count": 6
111
  },
112
  "Huggy.Policy.LearningRate.mean": {
113
+ "value": 3.413298862266661e-06,
114
+ "min": 3.413298862266661e-06,
115
+ "max": 4.192733602424999e-05,
116
+ "count": 6
117
  },
118
  "Huggy.Policy.LearningRate.sum": {
119
+ "value": 1.0239896586799983e-05,
120
+ "min": 1.0239896586799983e-05,
121
+ "max": 0.00010268711577104997,
122
+ "count": 6
123
  },
124
  "Huggy.Policy.Epsilon.mean": {
125
+ "value": 0.10113773333333335,
126
+ "min": 0.10113773333333335,
127
+ "max": 0.11397575000000001,
128
+ "count": 6
129
  },
130
  "Huggy.Policy.Epsilon.sum": {
131
+ "value": 0.30341320000000005,
132
+ "min": 0.20740874999999998,
133
+ "max": 0.33422895,
134
+ "count": 6
135
  },
136
  "Huggy.Policy.Beta.mean": {
137
+ "value": 6.677289333333323e-05,
138
+ "min": 6.677289333333323e-05,
139
+ "max": 0.0007073899249999999,
140
+ "count": 6
141
  },
142
  "Huggy.Policy.Beta.sum": {
143
+ "value": 0.00020031867999999967,
144
+ "min": 0.00020031867999999967,
145
+ "max": 0.0017380246049999997,
146
+ "count": 6
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1715403132",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1715403542"
160
  },
161
+ "total": 409.72195005000003,
162
  "count": 1,
163
+ "self": 0.6975756219994764,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05248374300026626,
167
  "count": 1,
168
+ "self": 0.05248374300026626
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 408.9718906850003,
172
  "count": 1,
173
+ "self": 0.7704747040106668,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.007888899000136,
177
  "count": 1,
178
+ "self": 2.007888899000136
179
  },
180
  "TrainerController.advance": {
181
+ "total": 406.0096471169891,
182
+ "count": 36691,
183
+ "self": 0.8032692929705263,
184
  "children": {
185
  "env_step": {
186
+ "total": 319.54335519294045,
187
+ "count": 36691,
188
+ "self": 264.3624791930438,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 54.68154378796453,
192
+ "count": 36691,
193
+ "self": 2.8692323229074645,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 51.812311465057064,
197
+ "count": 34675,
198
+ "self": 51.812311465057064
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.49933221193214194,
204
+ "count": 36691,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 407.4247572620234,
209
+ "count": 36691,
210
  "is_parallel": true,
211
+ "self": 195.24789342205622,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0009662999996180588,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0002793569992718403,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0006869430003462185,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0006869430003462185
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03032780100011223,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00038189099950614036,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000209771000299952,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000209771000299952
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.028929047000019636,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.028929047000019636
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0008070920002865023,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00023224400001709,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005748480002694123,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0005748480002694123
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 212.17686383996715,
271
+ "count": 36690,
272
  "is_parallel": true,
273
+ "self": 6.422632140981932,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 14.023024859949146,
277
+ "count": 36690,
278
  "is_parallel": true,
279
+ "self": 14.023024859949146
280
  },
281
  "communicator.exchange": {
282
+ "total": 176.51423545700436,
283
+ "count": 36690,
284
  "is_parallel": true,
285
+ "self": 176.51423545700436
286
  },
287
  "steps_from_proto": {
288
+ "total": 15.216971382031716,
289
+ "count": 36690,
290
  "is_parallel": true,
291
+ "self": 5.856577899080548,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 9.360393482951167,
295
+ "count": 73380,
296
  "is_parallel": true,
297
+ "self": 9.360393482951167
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 85.66302263107809,
311
+ "count": 36691,
312
+ "self": 1.0682843290087476,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 29.62631897106803,
316
+ "count": 36691,
317
+ "self": 29.222967418067583,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.4033515530004479,
321
+ "count": 2,
322
+ "self": 0.4033515530004479
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 54.968419331001314,
328
+ "count": 15,
329
+ "self": 44.20395680899719,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 10.764462522004123,
333
+ "count": 450,
334
+ "self": 10.764462522004123
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.600000359758269e-06,
344
  "count": 1,
345
+ "self": 1.600000359758269e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.18387836500005506,
349
  "count": 1,
350
+ "self": 0.006264383000143425,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.17761398199991163,
354
  "count": 1,
355
+ "self": 0.17761398199991163
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
  "Huggy": {
3
  "checkpoints": [
4
- {
5
- "steps": 199750,
6
- "file_path": "results/Huggy2/Huggy/Huggy-199750.onnx",
7
- "reward": 3.250019740702501,
8
- "creation_time": 1715400654.6284902,
9
- "auxillary_file_paths": [
10
- "results/Huggy2/Huggy/Huggy-199750.pt"
11
- ]
12
- },
13
- {
14
- "steps": 199983,
15
- "file_path": "results/Huggy2/Huggy/Huggy-199983.onnx",
16
- "reward": 1.5225059390068054,
17
- "creation_time": 1715400675.936896,
18
- "auxillary_file_paths": [
19
- "results/Huggy2/Huggy/Huggy-199983.pt"
20
- ]
21
- },
22
  {
23
  "steps": 399292,
24
  "file_path": "results/Huggy2/Huggy/Huggy-399292.onnx",
@@ -126,15 +108,42 @@
126
  "auxillary_file_paths": [
127
  "results/Huggy2/Huggy/Huggy-1689723.pt"
128
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
  }
130
  ],
131
  "final_checkpoint": {
132
- "steps": 1689723,
133
  "file_path": "results/Huggy2/Huggy.onnx",
134
- "reward": 3.9492963333129882,
135
- "creation_time": 1715403022.171419,
136
  "auxillary_file_paths": [
137
- "results/Huggy2/Huggy/Huggy-1689723.pt"
138
  ]
139
  }
140
  },
 
1
  {
2
  "Huggy": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 399292,
6
  "file_path": "results/Huggy2/Huggy/Huggy-399292.onnx",
 
108
  "auxillary_file_paths": [
109
  "results/Huggy2/Huggy/Huggy-1689723.pt"
110
  ]
111
+ },
112
+ {
113
+ "steps": 1799960,
114
+ "file_path": "results/Huggy2/Huggy/Huggy-1799960.onnx",
115
+ "reward": 4.282733224332333,
116
+ "creation_time": 1715403278.0461128,
117
+ "auxillary_file_paths": [
118
+ "results/Huggy2/Huggy/Huggy-1799960.pt"
119
+ ]
120
+ },
121
+ {
122
+ "steps": 1999985,
123
+ "file_path": "results/Huggy2/Huggy/Huggy-1999985.onnx",
124
+ "reward": 3.847782228142023,
125
+ "creation_time": 1715403541.7844296,
126
+ "auxillary_file_paths": [
127
+ "results/Huggy2/Huggy/Huggy-1999985.pt"
128
+ ]
129
+ },
130
+ {
131
+ "steps": 2000037,
132
+ "file_path": "results/Huggy2/Huggy/Huggy-2000037.onnx",
133
+ "reward": 3.8279934326807656,
134
+ "creation_time": 1715403541.9690402,
135
+ "auxillary_file_paths": [
136
+ "results/Huggy2/Huggy/Huggy-2000037.pt"
137
+ ]
138
  }
139
  ],
140
  "final_checkpoint": {
141
+ "steps": 2000037,
142
  "file_path": "results/Huggy2/Huggy.onnx",
143
+ "reward": 3.8279934326807656,
144
+ "creation_time": 1715403541.9690402,
145
  "auxillary_file_paths": [
146
+ "results/Huggy2/Huggy/Huggy-2000037.pt"
147
  ]
148
  }
149
  },