Hugging Face's logo

amihk
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
amihk commited on
Commit
9abfb91
·
verified ·
1 Parent(s): b4c3774

First Push

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +3 -0
  2. SnowballTarget/SnowballTarget-149984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-149984.pt +3 -0
  4. SnowballTarget/SnowballTarget-199984.onnx +3 -0
  5. SnowballTarget/SnowballTarget-199984.pt +3 -0
  6. SnowballTarget/SnowballTarget-200112.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200112.pt +3 -0
  8. SnowballTarget/SnowballTarget-49936.onnx +3 -0
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99960.pt +3 -0
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1761022616.6f01f057414c.2269.0 +3 -0
  14. run_logs/Player-0.log +13 -13
  15. run_logs/timers.json +157 -152
  16. run_logs/training_status.json +59 -1
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b183e4b5f5c1c67d74f2ba4911ba2fcfabf4bcbee7979f1235b1b1e6d45028ae
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2217868498183169af2cc70f193b575da6a3a5086072516a95fb2b79a6b564a
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2655b9a6e9466e1e02a8ce67a2f24283f231552c78c752539f307424950dc281
3
+ size 3849604
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b183e4b5f5c1c67d74f2ba4911ba2fcfabf4bcbee7979f1235b1b1e6d45028ae
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d5ccc178cd71d18a99f69dd314aeb24858d89e7f2470b047a448db91db20fe
3
+ size 3849604
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b183e4b5f5c1c67d74f2ba4911ba2fcfabf4bcbee7979f1235b1b1e6d45028ae
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09f2237f46a9a06db70b51f03c5420df3ee037dfee65bc039227590032c596e
3
+ size 3849604
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3de299015075f77e2f238022f6b482d0f2e602845f467c4004c22db813fe701
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ee164ddc59d153ca0bafae0a21d6877d4d2d1f368cdb3783ce3ef5dd8641af2
3
- size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680d3978d61e1c44b62f3a0a386e5668fad0c228c72cc304e204a8b76f1b6345
3
+ size 3849527
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29f369660ea096f5f207493c57240abb9189f3feaed9be258362c436e3a7827
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33530c3d772b403c0039da0e7995d22a5978ff1d1bc5ca3ef3e6dd8663c6cf57
3
+ size 3849527
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c677e764e080b17d16ce848edcb1baff396da1085ab2ca7450a17580a1790e7
3
- size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1329a6c5915077c0c89f0e645b9c051d5b643bacbe9c84b36c0c902e7e40ca2b
3
+ size 3848757
SnowballTarget/events.out.tfevents.1761022616.6f01f057414c.2269.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afe79acae713437d4b304eda3ffdf6ac59f12b11d12b0876ddc29ee3a61614d
3
+ size 28300
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ 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 0.149 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 +45,7 @@ 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: 0.634703 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.
@@ -53,7 +53,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 1355 frames, [16.0 KB-32.0 KB]: 22 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,19 +169,19 @@ 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
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 1378 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.2 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 1378 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.3 MB
@@ -213,13 +213,13 @@ 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]: 885 frames, [64.0 KB-128.0 KB]: 493 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 1378 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 1378 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 1377 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +249,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 1378 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 1378 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
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 0.147 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
  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: 1.155200 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.
 
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 39
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 7.1 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.3 MB
 
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]: 5127 frames, [64.0 KB-128.0 KB]: 331 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
 
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 5458 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.301649808883667,
6
- "min": 2.301649808883667,
7
- "max": 2.862959146499634,
8
- "count": 5
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 23495.240234375,
12
- "min": 23495.240234375,
13
- "max": 29225.0859375,
14
- "count": 5
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 49936.0,
18
  "min": 9952.0,
19
- "max": 49936.0,
20
- "count": 5
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 49936.0,
24
  "min": 9952.0,
25
- "max": 49936.0,
26
- "count": 5
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 4.717662811279297,
30
- "min": 0.48363935947418213,
31
- "max": 4.717662811279297,
32
- "count": 5
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 915.2265625,
36
- "min": 93.82603454589844,
37
- "max": 915.2265625,
38
- "count": 5
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07332339399926793,
42
- "min": 0.06873869095522654,
43
- "max": 0.07645749204938171,
44
- "count": 5
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.29329357599707173,
48
- "min": 0.28117907102055406,
49
- "max": 0.3822874602469086,
50
- "count": 5
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.24726582238194988,
54
- "min": 0.11396082191883276,
55
- "max": 0.26401323722858056,
56
- "count": 5
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.9890632895277995,
60
- "min": 0.45584328767533105,
61
- "max": 1.1439135331733552,
62
- "count": 5
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 0.000232482022506,
66
- "min": 0.000232482022506,
67
  "max": 0.000291882002706,
68
- "count": 5
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 0.000929928090024,
72
- "min": 0.000929928090024,
73
  "max": 0.00138516003828,
74
- "count": 5
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.17749400000000004,
78
- "min": 0.17749400000000004,
79
  "max": 0.19729400000000002,
80
- "count": 5
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.7099760000000002,
84
- "min": 0.7099760000000002,
85
  "max": 0.96172,
86
- "count": 5
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0038769506000000003,
90
- "min": 0.0038769506000000003,
91
  "max": 0.0048649706,
92
- "count": 5
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.015507802400000001,
96
- "min": 0.015507802400000001,
97
  "max": 0.023089828,
98
- "count": 5
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 5
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 5
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 12.704545454545455,
114
- "min": 3.3636363636363638,
115
- "max": 12.704545454545455,
116
- "count": 5
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 559.0,
120
- "min": 148.0,
121
- "max": 585.0,
122
- "count": 5
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 12.704545454545455,
126
- "min": 3.3636363636363638,
127
- "max": 12.704545454545455,
128
- "count": 5
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 559.0,
132
- "min": 148.0,
133
- "max": 585.0,
134
- "count": 5
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 5
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 5
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1761019509",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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": "2.9.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1761019628"
160
  },
161
- "total": 119.42312925100009,
162
  "count": 1,
163
- "self": 0.43217441999991024,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03770770599999196,
167
  "count": 1,
168
- "self": 0.03770770599999196
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 118.95324712500019,
172
  "count": 1,
173
- "self": 0.09231151100470925,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.979974828999957,
177
  "count": 1,
178
- "self": 2.979974828999957
179
  },
180
  "TrainerController.advance": {
181
- "total": 115.84689028699563,
182
- "count": 4592,
183
- "self": 0.0976514719923216,
184
  "children": {
185
  "env_step": {
186
- "total": 85.00400312399734,
187
- "count": 4592,
188
- "self": 66.68110533000026,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 18.267295503001833,
192
- "count": 4592,
193
- "self": 0.33164438101289306,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 17.93565112198894,
197
- "count": 4592,
198
- "self": 17.93565112198894
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.055602290995238945,
204
- "count": 4592,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 118.5250774750059,
209
- "count": 4592,
210
  "is_parallel": true,
211
- "self": 59.78065837200552,
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": 0.004782685999998648,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0029615690000355244,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0018211169999631238,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0018211169999631238
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03598463200000879,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006045650000032765,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.000426435000008496,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.000426435000008496
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03315368099993066,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03315368099993066
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0017999510000663577,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00033792600038395904,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014620249996823986,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014620249996823986
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 58.74441910300038,
271
- "count": 4591,
272
  "is_parallel": true,
273
- "self": 2.7859261469939156,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 1.465960488995961,
277
- "count": 4591,
278
  "is_parallel": true,
279
- "self": 1.465960488995961
280
  },
281
  "communicator.exchange": {
282
- "total": 44.57232552100072,
283
- "count": 4591,
284
  "is_parallel": true,
285
- "self": 44.57232552100072
286
  },
287
  "steps_from_proto": {
288
- "total": 9.920206946009785,
289
- "count": 4591,
290
  "is_parallel": true,
291
- "self": 1.7288534300023457,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 8.191353516007439,
295
- "count": 45910,
296
  "is_parallel": true,
297
- "self": 8.191353516007439
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 30.745235691005973,
311
- "count": 4592,
312
- "self": 0.11055861299178105,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 7.1566163880142994,
316
- "count": 4592,
317
- "self": 7.123809368014236,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.03280702000006386,
321
- "count": 1,
322
- "self": 0.03280702000006386
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 23.478060689999893,
328
- "count": 22,
329
- "self": 9.817086730996834,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 13.660973959003059,
333
- "count": 1119,
334
- "self": 13.660973959003059
335
  }
336
  }
337
  }
@@ -339,15 +339,20 @@
339
  }
340
  }
341
  },
 
 
 
 
 
342
  "TrainerController._save_models": {
343
- "total": 0.03407049799989181,
344
  "count": 1,
345
- "self": 3.8353999798346194e-05,
346
  "children": {
347
  "RLTrainer._checkpoint": {
348
- "total": 0.03403214400009347,
349
  "count": 1,
350
- "self": 0.03403214400009347
351
  }
352
  }
353
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8353955149650574,
6
+ "min": 0.8353955149650574,
7
+ "max": 2.8659350872039795,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7939.59912109375,
12
+ "min": 7939.59912109375,
13
+ "max": 29255.46484375,
14
+ "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
  "min": 9952.0,
19
+ "max": 199984.0,
20
+ "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
  "min": 9952.0,
25
+ "max": 199984.0,
26
+ "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.124088287353516,
30
+ "min": 0.46752145886421204,
31
+ "max": 13.124088287353516,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2559.197265625,
36
+ "min": 90.69916534423828,
37
+ "max": 2674.0556640625,
38
+ "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07516693794077225,
42
+ "min": 0.06325460929382483,
43
+ "max": 0.07691393329585872,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.300667751763089,
48
+ "min": 0.267610614154917,
49
+ "max": 0.37347195940246286,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19509169583519298,
54
+ "min": 0.12350139145365022,
55
+ "max": 0.29674913244796736,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7803667833407719,
60
+ "min": 0.49400556581460087,
61
+ "max": 1.4196480240891962,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 8.082097306000005e-06,
66
+ "min": 8.082097306000005e-06,
67
  "max": 0.000291882002706,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.232838922400002e-05,
72
+ "min": 3.232838922400002e-05,
73
  "max": 0.00138516003828,
74
+ "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10269400000000001,
78
+ "min": 0.10269400000000001,
79
  "max": 0.19729400000000002,
80
+ "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.41077600000000003,
84
+ "min": 0.41077600000000003,
85
  "max": 0.96172,
86
+ "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.0001444306000000001,
90
+ "min": 0.0001444306000000001,
91
  "max": 0.0048649706,
92
+ "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0005777224000000004,
96
+ "min": 0.0005777224000000004,
97
  "max": 0.023089828,
98
+ "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.863636363636363,
114
+ "min": 3.5454545454545454,
115
+ "max": 25.98181818181818,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1138.0,
120
+ "min": 156.0,
121
+ "max": 1429.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.863636363636363,
126
+ "min": 3.5454545454545454,
127
+ "max": 25.98181818181818,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1138.0,
132
+ "min": 156.0,
133
+ "max": 1429.0,
134
+ "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1761022615",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1761023190"
160
  },
161
+ "total": 575.53961044,
162
  "count": 1,
163
+ "self": 0.5932841290000397,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.042384856000012405,
167
  "count": 1,
168
+ "self": 0.042384856000012405
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 574.903941455,
172
  "count": 1,
173
+ "self": 0.6106686170012381,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.5144925110000145,
177
  "count": 1,
178
+ "self": 3.5144925110000145
179
  },
180
  "TrainerController.advance": {
181
+ "total": 570.7011342479988,
182
+ "count": 18192,
183
+ "self": 0.6751683960073933,
184
  "children": {
185
  "env_step": {
186
+ "total": 411.8355156769973,
187
+ "count": 18192,
188
+ "self": 357.6811618650073,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 53.78001844599345,
192
+ "count": 18192,
193
+ "self": 1.997040863989639,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 51.78297758200381,
197
+ "count": 18192,
198
+ "self": 51.78297758200381
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3743353659965578,
204
+ "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 571.9084978640066,
209
+ "count": 18192,
210
  "is_parallel": true,
211
+ "self": 262.78469562700326,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.006188243999986298,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003791403999969134,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002396840000017164,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002396840000017164
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04176972499999465,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007209940000052484,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004620530000352119,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004620530000352119
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03816016299998637,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03816016299998637
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0024265149999678215,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004330080000158887,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001993506999951933,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001993506999951933
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 309.1238022370033,
271
+ "count": 18191,
272
  "is_parallel": true,
273
+ "self": 14.404098239001485,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.441075482000713,
277
+ "count": 18191,
278
  "is_parallel": true,
279
+ "self": 7.441075482000713
280
  },
281
  "communicator.exchange": {
282
+ "total": 238.42589151400904,
283
+ "count": 18191,
284
  "is_parallel": true,
285
+ "self": 238.42589151400904
286
  },
287
  "steps_from_proto": {
288
+ "total": 48.85273700199207,
289
+ "count": 18191,
290
  "is_parallel": true,
291
+ "self": 8.82951286300056,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 40.02322413899151,
295
+ "count": 181910,
296
  "is_parallel": true,
297
+ "self": 40.02322413899151
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 158.19045017499406,
311
+ "count": 18192,
312
+ "self": 0.7998479510033576,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 30.497309548990586,
316
+ "count": 18192,
317
+ "self": 29.94256460499065,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5547449439999355,
321
+ "count": 4,
322
+ "self": 0.5547449439999355
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 126.89329267500011,
328
+ "count": 90,
329
+ "self": 48.637387447005835,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 78.25590522799428,
333
+ "count": 4587,
334
+ "self": 78.25590522799428
335
  }
336
  }
337
  }
 
339
  }
340
  }
341
  },
342
+ "trainer_threads": {
343
+ "total": 1.3970000054541742e-06,
344
+ "count": 1,
345
+ "self": 1.3970000054541742e-06
346
+ },
347
  "TrainerController._save_models": {
348
+ "total": 0.07764468200002739,
349
  "count": 1,
350
+ "self": 0.0009755959999893093,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.07666908600003808,
354
  "count": 1,
355
+ "self": 0.07666908600003808
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,7 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.2.0.dev0",
5
- "torch_version": "2.9.0+cu128"
6
  }
7
  }
 
1
  {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.727272727272727,
8
+ "creation_time": 1761022759.344575,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.0,
17
+ "creation_time": 1761022901.9467077,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.454545454545453,
26
+ "creation_time": 1761023046.3479362,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 27.363636363636363,
35
+ "creation_time": 1761023190.2465122,
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": 27.363636363636363,
44
+ "creation_time": 1761023190.3374739,
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": 27.363636363636363,
54
+ "creation_time": 1761023190.3374739,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.2.0.dev0",
63
+ "torch_version": "2.8.0+cu128"
64
  }
65
  }