Hugging Face's logo

YarramsettiNaresh
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
YarramsettiNaresh commited on
Commit
6f75465
·
1 Parent(s): c120f4f

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 +3 -0
  10. SnowballTarget/SnowballTarget-99960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99960.pt +3 -0
  12. SnowballTarget/checkpoint.pt +3 -0
  13. SnowballTarget/events.out.tfevents.1690176135.2067ae6e7397.4758.0 +3 -0
  14. run_logs/Player-0.log +15 -15
  15. run_logs/timers.json +159 -151
  16. run_logs/training_status.json +58 -0
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec6f5b53c55430655ad54fb85d6a812d2ee1add1182e07ae802e0bb1876960b
3
+ size 646532
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b766759e7153dd3e8f518f8214f19255d4e0b95475dc3fbbe8033b02da6fb601
3
+ size 646532
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b81647dc691e26f18c858b46a4746fc67d5017a796afa14fc6449c88fd95d5e
3
+ size 3843968
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec6f5b53c55430655ad54fb85d6a812d2ee1add1182e07ae802e0bb1876960b
3
+ size 646532
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58513d8d727168f326582b6dff25ab7876c318c594fcd4837f952c6530c33ef6
3
+ size 3843968
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec6f5b53c55430655ad54fb85d6a812d2ee1add1182e07ae802e0bb1876960b
3
+ size 646532
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e28c43923a492d9f08288b8de1bf15d6675c32496590090417e42dc659c20f
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd4450f858821eed2e6718269815af8b81cd672f4467669bf6ab5014c27bfae
3
+ size 646532
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b60f074f5ceae70f485e044ab5f1796826267a31699212d08ad792527e9365
3
+ size 3843968
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c301de55b8adfff46ccd0117cb246705379251ea15229c49d67d0fb929108bbd
3
+ size 646532
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf3b4d57539ac1555f85747aea4e69316ecf2422a9b5bac3b551cf4390aaea1
3
+ size 3843968
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e28c43923a492d9f08288b8de1bf15d6675c32496590090417e42dc659c20f
3
+ size 3843968
SnowballTarget/events.out.tfevents.1690176135.2067ae6e7397.4758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b3b3aab800e6a380bf7aa1fdc1ebd8b56bbc2691f46e54b00a31045ab0f4c4
3
+ size 28283
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 0.091 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: 0.687974 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 2 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]: 581 frames, [16.0 KB-32.0 KB]: 9 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
@@ -179,22 +179,22 @@ Memory Statistics:
179
  Peak Allocated Bytes 0 B
180
  Overflow Count 0
181
  [ALLOC_DEFAULT] Dual Thread Allocator
182
- Peak main deferred allocation count 40
183
  [ALLOC_BUCKET]
184
  Large Block size 4.0 MB
185
  Used Block count 1
186
  Peak Allocated bytes 1.0 MB
187
  [ALLOC_DEFAULT_MAIN]
188
- Peak usage frame count: [4.0 MB-8.0 MB]: 591 frames
189
  Requested Block Size 16.0 MB
190
  Peak Block count 1
191
- Peak Allocated memory 5.5 MB
192
  Peak Large allocation bytes 0 B
193
  [ALLOC_DEFAULT_THREAD]
194
- Peak usage frame count: [16.0 MB-32.0 MB]: 591 frames
195
  Requested Block Size 16.0 MB
196
  Peak Block count 1
197
- Peak Allocated memory 17.7 MB
198
  Peak Large allocation bytes 16.0 MB
199
  [ALLOC_TEMP_JOB_1_FRAME]
200
  Initial Block Size 2.0 MB
@@ -223,13 +223,13 @@ Memory Statistics:
223
  Used Block count 1
224
  Peak Allocated bytes 1.0 MB
225
  [ALLOC_GFX_MAIN]
226
- Peak usage frame count: [32.0 KB-64.0 KB]: 540 frames, [64.0 KB-128.0 KB]: 51 frames
227
  Requested Block Size 16.0 MB
228
  Peak Block count 1
229
- Peak Allocated memory 65.6 KB
230
  Peak Large allocation bytes 0 B
231
  [ALLOC_GFX_THREAD]
232
- Peak usage frame count: [32.0 KB-64.0 KB]: 591 frames
233
  Requested Block Size 16.0 MB
234
  Peak Block count 1
235
  Peak Allocated memory 39.6 KB
@@ -241,13 +241,13 @@ Memory Statistics:
241
  Used Block count 1
242
  Peak Allocated bytes 1.0 MB
243
  [ALLOC_CACHEOBJECTS_MAIN]
244
- Peak usage frame count: [0.5 MB-1.0 MB]: 591 frames
245
  Requested Block Size 4.0 MB
246
  Peak Block count 1
247
  Peak Allocated memory 0.6 MB
248
  Peak Large allocation bytes 0 B
249
  [ALLOC_CACHEOBJECTS_THREAD]
250
- Peak usage frame count: [0.5 MB-1.0 MB]: 590 frames, [2.0 MB-4.0 MB]: 1 frames
251
  Requested Block Size 4.0 MB
252
  Peak Block count 1
253
  Peak Allocated memory 2.2 MB
@@ -259,13 +259,13 @@ Memory Statistics:
259
  Used Block count 1
260
  Peak Allocated bytes 1.0 MB
261
  [ALLOC_TYPETREE_MAIN]
262
- Peak usage frame count: [0-1.0 KB]: 591 frames
263
  Requested Block Size 2.0 MB
264
  Peak Block count 1
265
  Peak Allocated memory 1.0 KB
266
  Peak Large allocation bytes 0 B
267
  [ALLOC_TYPETREE_THREAD]
268
- Peak usage frame count: [1.0 KB-2.0 KB]: 591 frames
269
  Requested Block Size 2.0 MB
270
  Peak Block count 1
271
  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 0.082 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: 0.752160 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 2 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]: 5370 frames, [16.0 KB-32.0 KB]: 91 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
 
179
  Peak Allocated Bytes 0 B
180
  Overflow Count 0
181
  [ALLOC_DEFAULT] Dual Thread Allocator
182
+ Peak main deferred allocation count 39
183
  [ALLOC_BUCKET]
184
  Large Block size 4.0 MB
185
  Used Block count 1
186
  Peak Allocated bytes 1.0 MB
187
  [ALLOC_DEFAULT_MAIN]
188
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
189
  Requested Block Size 16.0 MB
190
  Peak Block count 1
191
+ Peak Allocated memory 7.1 MB
192
  Peak Large allocation bytes 0 B
193
  [ALLOC_DEFAULT_THREAD]
194
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
195
  Requested Block Size 16.0 MB
196
  Peak Block count 1
197
+ Peak Allocated memory 17.3 MB
198
  Peak Large allocation bytes 16.0 MB
199
  [ALLOC_TEMP_JOB_1_FRAME]
200
  Initial Block Size 2.0 MB
 
223
  Used Block count 1
224
  Peak Allocated bytes 1.0 MB
225
  [ALLOC_GFX_MAIN]
226
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4591 frames, [64.0 KB-128.0 KB]: 871 frames
227
  Requested Block Size 16.0 MB
228
  Peak Block count 1
229
+ Peak Allocated memory 66.4 KB
230
  Peak Large allocation bytes 0 B
231
  [ALLOC_GFX_THREAD]
232
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
233
  Requested Block Size 16.0 MB
234
  Peak Block count 1
235
  Peak Allocated memory 39.6 KB
 
241
  Used Block count 1
242
  Peak Allocated bytes 1.0 MB
243
  [ALLOC_CACHEOBJECTS_MAIN]
244
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
245
  Requested Block Size 4.0 MB
246
  Peak Block count 1
247
  Peak Allocated memory 0.6 MB
248
  Peak Large allocation bytes 0 B
249
  [ALLOC_CACHEOBJECTS_THREAD]
250
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
251
  Requested Block Size 4.0 MB
252
  Peak Block count 1
253
  Peak Allocated memory 2.2 MB
 
259
  Used Block count 1
260
  Peak Allocated bytes 1.0 MB
261
  [ALLOC_TYPETREE_MAIN]
262
+ Peak usage frame count: [0-1.0 KB]: 5462 frames
263
  Requested Block Size 2.0 MB
264
  Peak Block count 1
265
  Peak Allocated memory 1.0 KB
266
  Peak Large allocation bytes 0 B
267
  [ALLOC_TYPETREE_THREAD]
268
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
269
  Requested Block Size 2.0 MB
270
  Peak Block count 1
271
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.7612252235412598,
6
- "min": 2.7612252235412598,
7
- "max": 2.8653252124786377,
8
- "count": 2
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 28459.94921875,
12
- "min": 28459.94921875,
13
- "max": 29438.3515625,
14
- "count": 2
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 19992.0,
18
  "min": 9952.0,
19
- "max": 19992.0,
20
- "count": 2
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 19992.0,
24
  "min": 9952.0,
25
- "max": 19992.0,
26
- "count": 2
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 1.2968162298202515,
30
- "min": 0.21842075884342194,
31
- "max": 1.2968162298202515,
32
- "count": 2
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 265.8473205566406,
36
- "min": 42.373626708984375,
37
- "max": 265.8473205566406,
38
- "count": 2
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 2
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 2
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07408841352569687,
54
- "min": 0.06308654767453131,
55
- "max": 0.07408841352569687,
56
- "count": 2
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.37044206762848436,
60
- "min": 0.25234619069812525,
61
- "max": 0.37044206762848436,
62
- "count": 2
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18859919219040405,
66
- "min": 0.09164527591087344,
67
- "max": 0.18859919219040405,
68
- "count": 2
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9429959609520202,
72
- "min": 0.3665811036434938,
73
- "max": 0.9429959609520202,
74
- "count": 2
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.000277032007656,
78
- "min": 0.000277032007656,
79
  "max": 0.000291882002706,
80
- "count": 2
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.00138516003828,
84
- "min": 0.001167528010824,
85
  "max": 0.00138516003828,
86
- "count": 2
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.19234400000000001,
90
- "min": 0.19234400000000001,
91
  "max": 0.19729400000000002,
92
- "count": 2
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.96172,
96
- "min": 0.7891760000000001,
97
  "max": 0.96172,
98
- "count": 2
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0046179656,
102
- "min": 0.0046179656,
103
  "max": 0.0048649706,
104
- "count": 2
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.023089828,
108
- "min": 0.0194598824,
109
  "max": 0.023089828,
110
- "count": 2
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 6.181818181818182,
114
- "min": 2.909090909090909,
115
- "max": 6.181818181818182,
116
- "count": 2
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 340.0,
120
- "min": 128.0,
121
- "max": 340.0,
122
- "count": 2
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 6.181818181818182,
126
- "min": 2.909090909090909,
127
- "max": 6.181818181818182,
128
- "count": 2
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 340.0,
132
- "min": 128.0,
133
- "max": 340.0,
134
- "count": 2
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 2
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 2
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1690135746",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
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": "0.31.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1690135790"
160
  },
161
- "total": 43.309494621,
162
  "count": 1,
163
- "self": 0.3260505649999459,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03050550000000385,
167
  "count": 1,
168
- "self": 0.03050550000000385
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 42.95293855600005,
172
  "count": 1,
173
- "self": 0.04939007500081516,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.044344598999942,
177
  "count": 1,
178
- "self": 4.044344598999942
179
  },
180
  "TrainerController.advance": {
181
- "total": 38.857473840999205,
182
- "count": 1967,
183
- "self": 0.024285636995273308,
184
  "children": {
185
  "env_step": {
186
- "total": 38.83318820400393,
187
- "count": 1967,
188
- "self": 27.999311967005724,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 10.809482877999471,
192
- "count": 1967,
193
- "self": 0.18097267299935993,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 10.628510205000111,
197
- "count": 1967,
198
- "self": 10.628510205000111
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.024393358998736403,
204
- "count": 1966,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 42.89934650800012,
209
- "count": 1966,
210
  "is_parallel": true,
211
- "self": 23.13832273599803,
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": 0.005689346000053774,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004274957000006907,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014143890000468673,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014143890000468673
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03500976499992703,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006329249998771047,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004087120000804134,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004087120000804134
244
  },
245
  "communicator.exchange": {
246
- "total": 0.031891209000036724,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.031891209000036724
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0020769189999327864,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00036559899979238253,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0017113200001404039,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0017113200001404039
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 19.76102377200209,
271
- "count": 1965,
272
  "is_parallel": true,
273
- "self": 0.9955926130041917,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.4977145240002301,
277
- "count": 1965,
278
  "is_parallel": true,
279
- "self": 0.4977145240002301
280
  },
281
  "communicator.exchange": {
282
- "total": 15.1581160699983,
283
- "count": 1965,
284
  "is_parallel": true,
285
- "self": 15.1581160699983
286
  },
287
  "steps_from_proto": {
288
- "total": 3.1096005649993685,
289
- "count": 1965,
290
  "is_parallel": true,
291
- "self": 0.553349789001004,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 2.5562507759983646,
295
- "count": 19650,
296
  "is_parallel": true,
297
- "self": 2.5562507759983646
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.534200002126454e-05,
313
  "count": 1,
314
- "self": 4.534200002126454e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,28 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 38.70046171801209,
324
- "count": 23758,
325
  "is_parallel": true,
326
- "self": 0.4699097920162103,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 22.2334682469957,
330
- "count": 23758,
331
  "is_parallel": true,
332
- "self": 22.2334682469957
 
 
 
 
 
 
 
 
333
  },
334
  "_update_policy": {
335
- "total": 15.997083679000184,
336
- "count": 9,
337
  "is_parallel": true,
338
- "self": 4.449693600998444,
339
  "children": {
340
  "TorchPPOOptimizer.update": {
341
- "total": 11.54739007800174,
342
- "count": 456,
343
  "is_parallel": true,
344
- "self": 11.54739007800174
345
  }
346
  }
347
  }
@@ -352,14 +360,14 @@
352
  }
353
  },
354
  "TrainerController._save_models": {
355
- "total": 0.001684699000065848,
356
  "count": 1,
357
- "self": 2.2007999973538972e-05,
358
  "children": {
359
  "RLTrainer._checkpoint": {
360
- "total": 0.001662691000092309,
361
  "count": 1,
362
- "self": 0.001662691000092309
363
  }
364
  }
365
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0581101179122925,
6
+ "min": 1.0581101179122925,
7
+ "max": 2.8736603260040283,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10126.1142578125,
12
+ "min": 10126.1142578125,
13
+ "max": 29460.765625,
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": 12.786876678466797,
30
+ "min": 0.42007485032081604,
31
+ "max": 12.786876678466797,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2493.44091796875,
36
+ "min": 81.49452209472656,
37
+ "max": 2602.491455078125,
38
+ "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06922008410733457,
54
+ "min": 0.06343485222713949,
55
+ "max": 0.07553110151233804,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2768803364293383,
60
+ "min": 0.2584552082877838,
61
+ "max": 0.3776555075616902,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2027629515630942,
66
+ "min": 0.12016408217217153,
67
+ "max": 0.28644669424085056,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8110518062523768,
72
+ "min": 0.48065632868868613,
73
+ "max": 1.4322334712042528,
74
+ "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000005e-06,
78
+ "min": 8.082097306000005e-06,
79
  "max": 0.000291882002706,
80
+ "count": 20
81
  },
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": {
89
+ "value": 0.10269400000000001,
90
+ "min": 0.10269400000000001,
91
  "max": 0.19729400000000002,
92
+ "count": 20
93
  },
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": {
101
+ "value": 0.0001444306000000001,
102
+ "min": 0.0001444306000000001,
103
  "max": 0.0048649706,
104
+ "count": 20
105
  },
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": 3.25,
115
+ "max": 25.318181818181817,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1098.0,
120
+ "min": 143.0,
121
+ "max": 1388.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.954545454545453,
126
+ "min": 3.25,
127
+ "max": 25.318181818181817,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1098.0,
132
+ "min": 143.0,
133
+ "max": 1388.0,
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": "1690176134",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
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": "0.31.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1690176517"
160
  },
161
+ "total": 382.38411989500014,
162
  "count": 1,
163
+ "self": 0.2748969490003219,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03201711599990631,
167
  "count": 1,
168
+ "self": 0.03201711599990631
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 382.0772058299999,
172
  "count": 1,
173
+ "self": 0.5058210050299294,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.112014843999987,
177
  "count": 1,
178
+ "self": 4.112014843999987
179
  },
180
  "TrainerController.advance": {
181
+ "total": 377.3209073719697,
182
+ "count": 18204,
183
+ "self": 0.23884082497397685,
184
  "children": {
185
  "env_step": {
186
+ "total": 377.08206654699575,
187
+ "count": 18204,
188
+ "self": 270.3380936220026,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 106.49914258599347,
192
+ "count": 18204,
193
+ "self": 1.4339597059824882,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 105.06518288001098,
197
+ "count": 18204,
198
+ "self": 105.06518288001098
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.24483033899969087,
204
+ "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 381.2773753730155,
209
+ "count": 18204,
210
  "is_parallel": true,
211
+ "self": 192.256163041033,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0056694060001518665,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004190550999965126,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014788550001867407,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014788550001867407
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.033565814999974464,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000665642000058142,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00034331799997744383,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00034331799997744383
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.030466515999933108,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.030466515999933108
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020903390000057698,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003696509995734232,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017206880004323466,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017206880004323466
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 189.0212123319825,
271
+ "count": 18203,
272
  "is_parallel": true,
273
+ "self": 9.154373794015783,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 4.619414255005495,
277
+ "count": 18203,
278
  "is_parallel": true,
279
+ "self": 4.619414255005495
280
  },
281
  "communicator.exchange": {
282
+ "total": 146.4987920099834,
283
+ "count": 18203,
284
  "is_parallel": true,
285
+ "self": 146.4987920099834
286
  },
287
  "steps_from_proto": {
288
+ "total": 28.74863227297783,
289
+ "count": 18203,
290
  "is_parallel": true,
291
+ "self": 5.20255184003031,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 23.54608043294752,
295
+ "count": 182030,
296
  "is_parallel": true,
297
+ "self": 23.54608043294752
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00015343300015047134,
313
  "count": 1,
314
+ "self": 0.00015343300015047134,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 376.0291802790109,
324
+ "count": 218975,
325
  "is_parallel": true,
326
+ "self": 4.337060073941075,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 206.82462146206944,
330
+ "count": 218975,
331
  "is_parallel": true,
332
+ "self": 206.0464459250693,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.778175537000152,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.778175537000152
339
+ }
340
+ }
341
  },
342
  "_update_policy": {
343
+ "total": 164.8674987430004,
344
+ "count": 90,
345
  "is_parallel": true,
346
+ "self": 45.155555061008954,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 119.71194368199144,
350
+ "count": 4587,
351
  "is_parallel": true,
352
+ "self": 119.71194368199144
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13830917600012071,
364
  "count": 1,
365
+ "self": 0.0008863590001055854,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13742281700001513,
369
  "count": 1,
370
+ "self": 0.13742281700001513
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,4 +1,62 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "0.31.0.dev0",
 
1
  {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.272727272727273,
8
+ "creation_time": 1690176234.8704717,
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": 20.545454545454547,
17
+ "creation_time": 1690176330.3026328,
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": 26.0,
26
+ "creation_time": 1690176424.6346245,
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": 24.363636363636363,
35
+ "creation_time": 1690176516.7414966,
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": 24.363636363636363,
44
+ "creation_time": 1690176516.9047394,
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": 24.363636363636363,
54
+ "creation_time": 1690176516.9047394,
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": "0.31.0.dev0",