Hugging Face's logo

neaven77
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
neaven77 commited on
Commit
277d4ab
·
verified ·
1 Parent(s): 9e0bbde

First Push

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200200.pt +3 -0
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1729300623.8f46b1b3b2b0.23013.0 +3 -0
  14. run_logs/Player-0.log +9 -12
  15. run_logs/timers.json +114 -114
  16. run_logs/training_status.json +17 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94e63e5004367e2128092067c0e2e4a4ef674179e05cb65a6bedff84288c7cad
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02306bed118b6dd473183973cbb63469c1b2e2b34f73dda1a27f59d88c03cf9f
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ea229eaec6184f63d41d9df9bdfa6500c961bc263d742814ef2c27e2880a8a2
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639ffd36a7fd81f434de77d4b3f207c30843e5a10ae02e0bf42d3053ab67a6df
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d095551a8fe038217cc8b3e2e52e278e695d30da3808683cd46554f00af4d980
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f7fb0f495ab73b4cb3a9f8a6189e2c1e2ed3a02d845a3491acad1489820b9d
3
  size 3849115
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94e63e5004367e2128092067c0e2e4a4ef674179e05cb65a6bedff84288c7cad
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02306bed118b6dd473183973cbb63469c1b2e2b34f73dda1a27f59d88c03cf9f
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb0c9d8b2383636c266918e7b2bf079a988bed94fa9f9c8cbede0505190652d5
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b76b6fcec525d9df97565dac6eb203b8f38070a3a02a47ff1dc790c3505da6e
3
  size 3849115
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02306bed118b6dd473183973cbb63469c1b2e2b34f73dda1a27f59d88c03cf9f
3
+ size 650646
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0a012074597836d129b6ccc1a5bc8caf41a57da2b2212ab54ec3159b8eb24a
3
+ size 3849115
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ec0efa422cabd7dde355a6f854da9a64a81cc6f1521fd4edf8d9578e3704dfd
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f25944506b28684040dfd416f12ce07204c1d88b4755233e050a8f02bcf0229
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50011a5b2e5f0aa42e0394dd70839f632ee123583cdd990f65f99007148c6513
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4226e3ecc21178ddbd9f5b1c392b5db74a925f3abaa9630fc7042d90418f2b5d
3
  size 3849040
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86e6b1f689d6c253b5ef6d1a44c40f6246e20c57dbc05a3a45b972106e06895a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245b4b74efe4a1103e2e844fbf9b90ddea68053f22299103231089f73d0e94ff
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f867cc3a4c4c586898c75cb0f0f714f199496bbd9fd8d7476409a8f9ad80e7bd
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80edcd75991f3171cba8b41424d39942d67a6aeb5b26f14f9ce502cccdfe333c
3
  size 3849040
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a392e84d53e5306fbdf00d36daf56bb759ec5df769570e2f5b063f4252a717d
3
  size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65908457f56a561019304bb46d93e67bdbdffa0b255ab1131a01250df4d17177
3
  size 3848290
SnowballTarget/events.out.tfevents.1729300623.8f46b1b3b2b0.23013.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d276aa2c204bb67504084a7ff8300ef80ab6eadbdbb9866369303d7073b339
3
+ size 23990
run_logs/Player-0.log CHANGED
@@ -1,12 +1,9 @@
1
- Mono path[0] = '/content/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
- Mono config path = '/content/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
- [Subsystems] Discovering subsystems at path /content/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
11
  GfxDevice: creating device client; threaded=0; jobified=0
12
  NullGfxDevice:
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.310 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 1.196951 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -61,7 +58,7 @@ Memory Statistics:
61
  [ALLOC_TEMP_Loading.AsyncRead]
62
  Initial Block Size 64.0 KB
63
  Current Block Size 64.0 KB
64
- Peak Allocated Bytes 178 B
65
  Overflow Count 0
66
  [ALLOC_TEMP_Loading.PreloadManager]
67
  Initial Block Size 256.0 KB
@@ -169,7 +166,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -213,10 +210,10 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4786 frames, [64.0 KB-128.0 KB]: 675 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
 
1
+ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
+ Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
+ [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
8
  GfxDevice: creating device client; threaded=0; jobified=0
9
  NullGfxDevice:
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.131 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.872210 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
58
  [ALLOC_TEMP_Loading.AsyncRead]
59
  Initial Block Size 64.0 KB
60
  Current Block Size 64.0 KB
61
+ Peak Allocated Bytes 198 B
62
  Overflow Count 0
63
  [ALLOC_TEMP_Loading.PreloadManager]
64
  Initial Block Size 256.0 KB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5204 frames, [64.0 KB-128.0 KB]: 257 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.7 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9459468126296997,
6
- "min": 0.9459468126296997,
7
- "max": 2.8689796924591064,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9052.7109375,
12
- "min": 9052.7109375,
13
- "max": 30029.052734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.77916145324707,
30
- "min": 0.33034974336624146,
31
- "max": 12.77916145324707,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2491.9365234375,
36
- "min": 64.08785247802734,
37
- "max": 2576.0830078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06525618364230468,
54
- "min": 0.06303111526786405,
55
- "max": 0.07087165144712701,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2610247345692187,
60
- "min": 0.2521244610714562,
61
- "max": 0.3543582572356351,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1929877455912384,
66
- "min": 0.11757814990899837,
67
- "max": 0.29391449361163025,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7719509823649536,
72
- "min": 0.4703125996359935,
73
- "max": 1.402781379865665,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -82,7 +82,7 @@
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
  "value": 3.232838922400002e-05,
84
  "min": 3.232838922400002e-05,
85
- "max": 0.0013850280383239997,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -94,7 +94,7 @@
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
  "value": 0.41077600000000003,
96
  "min": 0.41077600000000003,
97
- "max": 0.961676,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
@@ -106,31 +106,31 @@
106
  "SnowballTarget.Policy.Beta.sum": {
107
  "value": 0.0005777224000000004,
108
  "min": 0.0005777224000000004,
109
- "max": 0.023087632400000002,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.34090909090909,
114
- "min": 3.522727272727273,
115
- "max": 25.34090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1115.0,
120
- "min": 155.0,
121
- "max": 1379.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.34090909090909,
126
- "min": 3.522727272727273,
127
- "max": 25.34090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1115.0,
132
- "min": 155.0,
133
- "max": 1379.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1729299395",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.4.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1729299969"
160
  },
161
- "total": 574.2774803270004,
162
  "count": 1,
163
- "self": 0.6067967130002216,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.07879439699991053,
167
  "count": 1,
168
- "self": 0.07879439699991053
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 573.5918892170002,
172
  "count": 1,
173
- "self": 0.8665863720343623,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 7.24483100299949,
177
  "count": 1,
178
- "self": 7.24483100299949
179
  },
180
  "TrainerController.advance": {
181
- "total": 565.3881664589671,
182
- "count": 18202,
183
- "self": 0.4058235519705704,
184
  "children": {
185
  "env_step": {
186
- "total": 564.9823429069966,
187
- "count": 18202,
188
- "self": 436.21090926804845,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 128.36039453993817,
192
- "count": 18202,
193
- "self": 2.1942811589506164,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 126.16611338098755,
197
- "count": 18202,
198
- "self": 126.16611338098755
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.4110390990099404,
204
- "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 571.7181056699837,
209
- "count": 18202,
210
  "is_parallel": true,
211
- "self": 272.5084911410295,
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": 0.007752369000627368,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.005363989999750629,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002388379000876739,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002388379000876739
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0507054710005832,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008231360006902833,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005003549995308276,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005003549995308276
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04686170900004072,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04686170900004072
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0025202710003213724,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004810370010090992,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0020392339993122732,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0020392339993122732
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 299.20961452895426,
271
- "count": 18201,
272
  "is_parallel": true,
273
- "self": 14.25094045581045,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.174774254993281,
277
- "count": 18201,
278
  "is_parallel": true,
279
- "self": 7.174774254993281
280
  },
281
  "communicator.exchange": {
282
- "total": 234.56327226712074,
283
- "count": 18201,
284
  "is_parallel": true,
285
- "self": 234.56327226712074
286
  },
287
  "steps_from_proto": {
288
- "total": 43.22062755102979,
289
- "count": 18201,
290
  "is_parallel": true,
291
- "self": 8.609145336943584,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 34.61148221408621,
295
- "count": 182010,
296
  "is_parallel": true,
297
- "self": 34.61148221408621
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0002611089994388749,
313
  "count": 1,
314
- "self": 0.0002611089994388749,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 558.6276691082085,
324
- "count": 761365,
325
  "is_parallel": true,
326
- "self": 17.316953554231077,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 300.38377538597797,
330
- "count": 761365,
331
  "is_parallel": true,
332
- "self": 299.20763793997867,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.1761374459993021,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.1761374459993021
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 240.92694016799942,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 71.99210650799978,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 168.93483365999964,
350
  "count": 4584,
351
  "is_parallel": true,
352
- "self": 168.93483365999964
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09204427399981796,
364
  "count": 1,
365
- "self": 0.0013540400004785624,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.0906902339993394,
369
  "count": 1,
370
- "self": 0.0906902339993394
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9282233119010925,
6
+ "min": 0.9282233119010925,
7
+ "max": 2.8571064472198486,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8872.88671875,
12
+ "min": 8872.88671875,
13
+ "max": 29291.0546875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.746694564819336,
30
+ "min": 0.354756623506546,
31
+ "max": 12.746694564819336,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2485.60546875,
36
+ "min": 68.82278442382812,
37
+ "max": 2591.01708984375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0674808266327697,
54
+ "min": 0.060206140000624214,
55
+ "max": 0.07240911743761613,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2699233065310788,
60
+ "min": 0.24082456000249686,
61
+ "max": 0.3586490299077887,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2002700192890331,
66
+ "min": 0.12406513871460716,
67
+ "max": 0.28250086599705265,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8010800771561324,
72
+ "min": 0.4962605548584286,
73
+ "max": 1.4125043299852633,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
  "value": 3.232838922400002e-05,
84
  "min": 3.232838922400002e-05,
85
+ "max": 0.00138516003828,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
 
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
  "value": 0.41077600000000003,
96
  "min": 0.41077600000000003,
97
+ "max": 0.96172,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
 
106
  "SnowballTarget.Policy.Beta.sum": {
107
  "value": 0.0005777224000000004,
108
  "min": 0.0005777224000000004,
109
+ "max": 0.023089828,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.954545454545453,
114
+ "min": 3.340909090909091,
115
+ "max": 25.054545454545455,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1098.0,
120
+ "min": 147.0,
121
+ "max": 1378.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.954545454545453,
126
+ "min": 3.340909090909091,
127
+ "max": 25.054545454545455,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1098.0,
132
+ "min": 147.0,
133
+ "max": 1378.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1729300622",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.4.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1729301195"
160
  },
161
+ "total": 573.0838532140006,
162
  "count": 1,
163
+ "self": 0.5404820090006979,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.08223738800006686,
167
  "count": 1,
168
+ "self": 0.08223738800006686
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 572.4611338169998,
172
  "count": 1,
173
+ "self": 0.8968332049807941,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.054462130000502,
177
  "count": 1,
178
+ "self": 2.054462130000502
179
  },
180
  "TrainerController.advance": {
181
+ "total": 569.4189443550185,
182
+ "count": 18203,
183
+ "self": 0.43013124091612553,
184
  "children": {
185
  "env_step": {
186
+ "total": 568.9888131141024,
187
+ "count": 18203,
188
+ "self": 438.292979754151,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 130.29416343905177,
192
+ "count": 18203,
193
+ "self": 2.298808769999596,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 127.99535466905218,
197
+ "count": 18203,
198
+ "self": 127.99535466905218
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4016699208996215,
204
+ "count": 18203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 570.6115949860714,
209
+ "count": 18203,
210
  "is_parallel": true,
211
+ "self": 266.88652347299194,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003393527999833168,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0011108759990747785,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0022826520007583895,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0022826520007583895
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04615061799995601,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000915324000743567,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00047664599969721166,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00047664599969721166
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04207351999957609,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04207351999957609
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002685127999939141,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004993579987058183,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0021857700012333225,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0021857700012333225
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 303.72507151307946,
271
+ "count": 18202,
272
  "is_parallel": true,
273
+ "self": 14.63684295802068,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.397761070020351,
277
+ "count": 18202,
278
  "is_parallel": true,
279
+ "self": 7.397761070020351
280
  },
281
  "communicator.exchange": {
282
+ "total": 238.48928855608574,
283
+ "count": 18202,
284
  "is_parallel": true,
285
+ "self": 238.48928855608574
286
  },
287
  "steps_from_proto": {
288
+ "total": 43.201178928952686,
289
+ "count": 18202,
290
  "is_parallel": true,
291
+ "self": 8.431372530801127,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 34.76980639815156,
295
+ "count": 182020,
296
  "is_parallel": true,
297
+ "self": 34.76980639815156
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0002099090006595361,
313
  "count": 1,
314
+ "self": 0.0002099090006595361,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 562.6710339836636,
324
+ "count": 774614,
325
  "is_parallel": true,
326
+ "self": 17.5894138624235,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 306.28731542324203,
330
+ "count": 774614,
331
  "is_parallel": true,
332
+ "self": 305.6523715372423,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.6349438859997463,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.6349438859997463
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 238.7943046979981,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 69.2997793920058,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 169.49452530599228,
350
  "count": 4584,
351
  "is_parallel": true,
352
+ "self": 169.49452530599228
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09068421799929638,
364
  "count": 1,
365
+ "self": 0.0013885809994462761,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.0892956369998501,
369
  "count": 1,
370
+ "self": 0.0892956369998501
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.727272727272727,
8
- "creation_time": 1729299542.6841261,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 21.363636363636363,
17
- "creation_time": 1729299683.5740452,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.545454545454547,
26
- "creation_time": 1729299826.9956923,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,29 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.0,
35
- "creation_time": 1729299968.7796206,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.0,
44
- "creation_time": 1729299968.904378,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.0,
54
- "creation_time": 1729299968.904378,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.909090909090908,
8
+ "creation_time": 1729300766.4663393,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 20.09090909090909,
17
+ "creation_time": 1729300908.7523146,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 23.454545454545453,
26
+ "creation_time": 1729301051.6301224,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 24.454545454545453,
35
+ "creation_time": 1729301194.967714,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 24.363636363636363,
44
+ "creation_time": 1729301195.1095746,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 24.363636363636363,
54
+ "creation_time": 1729301195.1095746,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },