Hugging Face's logo

inkasaras
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
inkasaras commited on
Commit
64dfc80
•
1 Parent(s): efcf543

First Push

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/{SnowballTarget-11576.onnx → SnowballTarget-149984.onnx} +1 -1
  3. SnowballTarget/{SnowballTarget-11576.pt → SnowballTarget-149984.pt} +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +3 -0
  5. SnowballTarget/SnowballTarget-199984.pt +3 -0
  6. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200200.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 +1 -1
  13. SnowballTarget/{events.out.tfevents.1679087846.f747f017bcf1.2117.0 → events.out.tfevents.1679318889.f97424387021.12139.0} +2 -2
  14. run_logs/Player-0.log +14 -15
  15. run_logs/timers.json +162 -154
  16. run_logs/training_status.json +45 -9
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0438c442a5c3b6da49aa7bf6a9a0af11456fd5aae8c0ca0a910522087a1be7d0
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881972c70a73820210b3bc2479dd410e1a7bb00634a4a996a9fe1d608bdd4586
3
  size 646532
SnowballTarget/{SnowballTarget-11576.onnx → SnowballTarget-149984.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0438c442a5c3b6da49aa7bf6a9a0af11456fd5aae8c0ca0a910522087a1be7d0
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f1becee96776bb1155e56d99d03b1b0c40f49354444cd4b7ded3434cb98879
3
  size 646532
SnowballTarget/{SnowballTarget-11576.pt → SnowballTarget-149984.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7173ef5a56630bd9fdd796d76d0f479cfee8bf869281bc8ef73c816e2ead414
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d3c2855479c1c79311908352832c98c70f3d9245c110e02776bdd2a2db9435
3
  size 3843968
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881972c70a73820210b3bc2479dd410e1a7bb00634a4a996a9fe1d608bdd4586
3
+ size 646532
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2948e0bb93ae223e57ac6917703150e1e747574c9dbb317ad9a6ba22a68585c9
3
+ size 3843968
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881972c70a73820210b3bc2479dd410e1a7bb00634a4a996a9fe1d608bdd4586
3
+ size 646532
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c65648d5da00cfb4b965cc5950faa6044baca5d768646508160046361a0069e
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5770236424299d7dd9280e90caaa230521229e0d82530ce5fc9f6b700a0648
3
+ size 646532
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d6eb27869fd341f26cd0b113ac25631907a9fd618da733e65634988437454d
3
+ size 3843968
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a189d5a445a952fdc8a6ddec157e2d7d7a1d41b4437ba1c6b96f79bd22f7bcfb
3
+ size 646532
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c596f79630afc66cbf2472638de45bf47bc088e962c0482bc0f74c44a9eeb00
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7173ef5a56630bd9fdd796d76d0f479cfee8bf869281bc8ef73c816e2ead414
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c65648d5da00cfb4b965cc5950faa6044baca5d768646508160046361a0069e
3
  size 3843968
SnowballTarget/{events.out.tfevents.1679087846.f747f017bcf1.2117.0 → events.out.tfevents.1679318889.f97424387021.12139.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46e3b1d5427b59f5c8eb182e8ac98227c7eb5c5eddffa7d5209a4c7ed87ed707
3
- size 6798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f47ed28b175bab57d1ba5ceabc19406be8000d931de7ebd99324b7b6596564c
3
+ size 28137
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(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 0.082 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)
@@ -45,16 +45,15 @@ 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: 1.116642 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
- GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
  Setting up 1 worker threads for Enlighten.
53
  Memory Statistics:
54
  [ALLOC_TEMP_TLS] TLS Allocator
55
  StackAllocators :
56
  [ALLOC_TEMP_MAIN]
57
- Peak usage frame count: [8.0 KB-16.0 KB]: 316 frames, [16.0 KB-32.0 KB]: 5 frames, [2.0 MB-4.0 MB]: 1 frames
58
  Initial Block Size 4.0 MB
59
  Current Block Size 4.0 MB
60
  Peak Allocated Bytes 2.0 MB
@@ -170,19 +169,19 @@ Memory Statistics:
170
  Peak Allocated Bytes 0 B
171
  Overflow Count 0
172
  [ALLOC_DEFAULT] Dual Thread Allocator
173
- Peak main deferred allocation count 34
174
  [ALLOC_BUCKET]
175
  Large Block size 4.0 MB
176
  Used Block count 1
177
  Peak Allocated bytes 1.0 MB
178
  [ALLOC_DEFAULT_MAIN]
179
- Peak usage frame count: [4.0 MB-8.0 MB]: 322 frames
180
  Requested Block Size 16.0 MB
181
  Peak Block count 1
182
- Peak Allocated memory 5.4 MB
183
  Peak Large allocation bytes 0 B
184
  [ALLOC_DEFAULT_THREAD]
185
- Peak usage frame count: [16.0 MB-32.0 MB]: 322 frames
186
  Requested Block Size 16.0 MB
187
  Peak Block count 1
188
  Peak Allocated memory 17.7 MB
@@ -214,13 +213,13 @@ Memory Statistics:
214
  Used Block count 1
215
  Peak Allocated bytes 1.0 MB
216
  [ALLOC_GFX_MAIN]
217
- Peak usage frame count: [32.0 KB-64.0 KB]: 276 frames, [64.0 KB-128.0 KB]: 46 frames
218
  Requested Block Size 16.0 MB
219
  Peak Block count 1
220
- Peak Allocated memory 65.6 KB
221
  Peak Large allocation bytes 0 B
222
  [ALLOC_GFX_THREAD]
223
- Peak usage frame count: [32.0 KB-64.0 KB]: 322 frames
224
  Requested Block Size 16.0 MB
225
  Peak Block count 1
226
  Peak Allocated memory 39.6 KB
@@ -232,13 +231,13 @@ Memory Statistics:
232
  Used Block count 1
233
  Peak Allocated bytes 1.0 MB
234
  [ALLOC_CACHEOBJECTS_MAIN]
235
- Peak usage frame count: [0.5 MB-1.0 MB]: 322 frames
236
  Requested Block Size 4.0 MB
237
  Peak Block count 1
238
  Peak Allocated memory 0.6 MB
239
  Peak Large allocation bytes 0 B
240
  [ALLOC_CACHEOBJECTS_THREAD]
241
- Peak usage frame count: [0.5 MB-1.0 MB]: 321 frames, [2.0 MB-4.0 MB]: 1 frames
242
  Requested Block Size 4.0 MB
243
  Peak Block count 1
244
  Peak Allocated memory 2.2 MB
@@ -250,13 +249,13 @@ Memory Statistics:
250
  Used Block count 1
251
  Peak Allocated bytes 1.0 MB
252
  [ALLOC_TYPETREE_MAIN]
253
- Peak usage frame count: [0-1.0 KB]: 322 frames
254
  Requested Block Size 2.0 MB
255
  Peak Block count 1
256
  Peak Allocated memory 1.0 KB
257
  Peak Large allocation bytes 0 B
258
  [ALLOC_TYPETREE_THREAD]
259
- Peak usage frame count: [1.0 KB-2.0 KB]: 322 frames
260
  Requested Block Size 2.0 MB
261
  Peak Block count 1
262
  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 0.078 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: 0.917074 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.
52
  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]: 5369 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
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 37
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]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.7 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]: 4632 frames, [64.0 KB-128.0 KB]: 829 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]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.867946147918701,
6
- "min": 2.867946147918701,
7
- "max": 2.867946147918701,
8
- "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 29433.732421875,
12
- "min": 29433.732421875,
13
- "max": 29433.732421875,
14
- "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 9952.0,
18
  "min": 9952.0,
19
- "max": 9952.0,
20
- "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 9952.0,
24
  "min": 9952.0,
25
- "max": 9952.0,
26
- "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.36501964926719666,
30
- "min": 0.36501964926719666,
31
- "max": 0.36501964926719666,
32
- "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 70.81381225585938,
36
- "min": 70.81381225585938,
37
- "max": 70.81381225585938,
38
- "count": 1
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 1
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
- "max": 8756.0,
50
- "count": 1
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06009695729764586,
54
- "min": 0.06009695729764586,
55
- "max": 0.06009695729764586,
56
- "count": 1
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.24038782919058344,
60
- "min": 0.24038782919058344,
61
- "max": 0.24038782919058344,
62
- "count": 1
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.11938250649209116,
66
- "min": 0.11938250649209116,
67
- "max": 0.11938250649209116,
68
- "count": 1
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.47753002596836464,
72
- "min": 0.47753002596836464,
73
- "max": 0.47753002596836464,
74
- "count": 1
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.000291882002706,
78
- "min": 0.000291882002706,
79
  "max": 0.000291882002706,
80
- "count": 1
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.001167528010824,
84
- "min": 0.001167528010824,
85
- "max": 0.001167528010824,
86
- "count": 1
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.19729400000000002,
90
- "min": 0.19729400000000002,
91
  "max": 0.19729400000000002,
92
- "count": 1
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.7891760000000001,
96
- "min": 0.7891760000000001,
97
- "max": 0.7891760000000001,
98
- "count": 1
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0048649706,
102
- "min": 0.0048649706,
103
  "max": 0.0048649706,
104
- "count": 1
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0194598824,
108
- "min": 0.0194598824,
109
- "max": 0.0194598824,
110
- "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 3.6136363636363638,
114
- "min": 3.6136363636363638,
115
- "max": 3.6136363636363638,
116
- "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 159.0,
120
- "min": 159.0,
121
- "max": 159.0,
122
- "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 3.6136363636363638,
126
- "min": 3.6136363636363638,
127
- "max": 3.6136363636363638,
128
- "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 159.0,
132
- "min": 159.0,
133
- "max": 159.0,
134
- "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1679087839",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
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": "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": "1679087877"
160
  },
161
- "total": 37.19952396700006,
162
  "count": 1,
163
- "self": 0.18337441200009152,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10661946999999827,
167
  "count": 1,
168
- "self": 0.10661946999999827
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 36.90953008499997,
172
  "count": 1,
173
- "self": 0.14344037400132947,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 10.20520952999999,
177
  "count": 1,
178
- "self": 10.20520952999999
179
  },
180
  "TrainerController.advance": {
181
- "total": 26.113130139998702,
182
- "count": 1073,
183
- "self": 0.015438158999131701,
184
  "children": {
185
  "env_step": {
186
- "total": 26.09769198099957,
187
- "count": 1073,
188
- "self": 19.096851784999217,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 6.985853050999594,
192
- "count": 1073,
193
- "self": 0.20996643500183154,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 6.775886615997763,
197
- "count": 1073,
198
- "self": 6.775886615997763
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.014987145000759483,
204
- "count": 1072,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 36.362026185999696,
209
- "count": 1072,
210
  "is_parallel": true,
211
- "self": 22.53656574799936,
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": 0.00622794100002011,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0047879080000825525,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014400329999375572,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014400329999375572
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04782305899999528,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006204030000276362,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00027903400001605405,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00027903400001605405
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04514546299998301,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04514546299998301
250
  },
251
  "steps_from_proto": {
252
- "total": 0.001778158999968582,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003690989998972327,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014090600000713494,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014090600000713494
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 13.825460438000334,
271
- "count": 1071,
272
  "is_parallel": true,
273
- "self": 0.5667811729985033,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.30566426999985197,
277
- "count": 1071,
278
  "is_parallel": true,
279
- "self": 0.30566426999985197
280
  },
281
  "communicator.exchange": {
282
- "total": 11.150007539001876,
283
- "count": 1071,
284
  "is_parallel": true,
285
- "self": 11.150007539001876
286
  },
287
  "steps_from_proto": {
288
- "total": 1.8030074560001026,
289
- "count": 1071,
290
  "is_parallel": true,
291
- "self": 0.3532421949989839,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 1.4497652610011187,
295
- "count": 10710,
296
  "is_parallel": true,
297
- "self": 1.4497652610011187
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011445600000570266,
313
  "count": 1,
314
- "self": 0.00011445600000570266,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,28 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 26.023509298995577,
324
- "count": 22192,
325
  "is_parallel": true,
326
- "self": 0.5657549129856534,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 14.718005123009846,
330
- "count": 22192,
331
  "is_parallel": true,
332
- "self": 14.718005123009846
 
 
 
 
 
 
 
 
333
  },
334
  "_update_policy": {
335
- "total": 10.739749263000078,
336
- "count": 5,
337
  "is_parallel": true,
338
- "self": 3.8587524820004546,
339
  "children": {
340
  "TorchPPOOptimizer.update": {
341
- "total": 6.880996780999624,
342
- "count": 252,
343
  "is_parallel": true,
344
- "self": 6.880996780999624
345
  }
346
  }
347
  }
@@ -352,14 +360,14 @@
352
  }
353
  },
354
  "TrainerController._save_models": {
355
- "total": 0.4476355849999436,
356
  "count": 1,
357
- "self": 0.001131046999944374,
358
  "children": {
359
  "RLTrainer._checkpoint": {
360
- "total": 0.44650453799999923,
361
  "count": 1,
362
- "self": 0.44650453799999923
363
  }
364
  }
365
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9422412514686584,
6
+ "min": 0.9422412514686584,
7
+ "max": 2.8664231300354004,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8996.51953125,
12
+ "min": 8996.51953125,
13
+ "max": 29418.1015625,
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": 12.755426406860352,
30
+ "min": 0.3794362246990204,
31
+ "max": 12.755426406860352,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2487.30810546875,
36
+ "min": 73.61062622070312,
37
+ "max": 2554.177734375,
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": 0.0635759476184224,
54
+ "min": 0.06257579988153998,
55
+ "max": 0.07587045722888719,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2543037904736896,
60
+ "min": 0.2503031995261599,
61
+ "max": 0.35930167196299106,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.22818079554274973,
66
+ "min": 0.10669318321343584,
67
+ "max": 0.2895609795608941,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.9127231821709989,
72
+ "min": 0.42677273285374334,
73
+ "max": 1.382171713254031,
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": 25.545454545454547,
114
+ "min": 3.2954545454545454,
115
+ "max": 25.545454545454547,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1124.0,
120
+ "min": 145.0,
121
+ "max": 1370.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.545454545454547,
126
+ "min": 3.2954545454545454,
127
+ "max": 25.545454545454547,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1124.0,
132
+ "min": 145.0,
133
+ "max": 1370.0,
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": "1679318884",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
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": "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": "1679319358"
160
  },
161
+ "total": 474.1336049300003,
162
  "count": 1,
163
+ "self": 0.44009861300082775,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10474744799967084,
167
  "count": 1,
168
+ "self": 0.10474744799967084
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 473.5887588689998,
172
  "count": 1,
173
+ "self": 0.5665627350003888,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 8.395298228000229,
177
  "count": 1,
178
+ "self": 8.395298228000229
179
  },
180
  "TrainerController.advance": {
181
+ "total": 464.4802571139994,
182
+ "count": 18201,
183
+ "self": 0.30488606099243043,
184
  "children": {
185
  "env_step": {
186
+ "total": 464.175371053007,
187
+ "count": 18201,
188
+ "self": 331.02882855100825,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 132.86095986002965,
192
+ "count": 18201,
193
+ "self": 1.9866540410271227,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 130.87430581900253,
197
+ "count": 18201,
198
+ "self": 130.87430581900253
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.28558264196908567,
204
+ "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 472.0981763350119,
209
+ "count": 18201,
210
  "is_parallel": true,
211
+ "self": 226.85456594302605,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005014638000375271,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003511779999371356,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001502858001003915,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001502858001003915
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05999726500022007,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006575510001312068,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00036095299992666696,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00036095299992666696
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.05704352500015375,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.05704352500015375
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019352360000084445,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00038361299948519445,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.00155162300052325,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.00155162300052325
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 245.24361039198584,
271
+ "count": 18200,
272
  "is_parallel": true,
273
+ "self": 9.71383036793668,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.381093901034546,
277
+ "count": 18200,
278
  "is_parallel": true,
279
+ "self": 5.381093901034546
280
  },
281
  "communicator.exchange": {
282
+ "total": 197.00245327702442,
283
+ "count": 18200,
284
  "is_parallel": true,
285
+ "self": 197.00245327702442
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.1462328459902,
289
+ "count": 18200,
290
  "is_parallel": true,
291
+ "self": 6.711429257994041,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.434803587996157,
295
+ "count": 182000,
296
  "is_parallel": true,
297
+ "self": 26.434803587996157
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00013724099972023396,
313
  "count": 1,
314
+ "self": 0.00013724099972023396,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 460.782650840119,
324
+ "count": 423871,
325
  "is_parallel": true,
326
+ "self": 10.91858612734859,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 258.4001306387713,
330
+ "count": 423871,
331
  "is_parallel": true,
332
+ "self": 257.5405520917716,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.8595785469997281,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.8595785469997281
339
+ }
340
+ }
341
  },
342
  "_update_policy": {
343
+ "total": 191.4639340739991,
344
+ "count": 90,
345
  "is_parallel": true,
346
+ "self": 69.95742427200184,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 121.50650980199725,
350
+ "count": 4584,
351
  "is_parallel": true,
352
+ "self": 121.50650980199725
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14650355100002344,
364
  "count": 1,
365
+ "self": 0.000982899000064208,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14552065199995923,
369
  "count": 1,
370
+ "self": 0.14552065199995923
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,22 +2,58 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 11576,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.onnx",
7
- "reward": 5.2727272727272725,
8
- "creation_time": 1679087876.8157299,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 11576,
16
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
- "reward": 5.2727272727272725,
18
- "creation_time": 1679087876.8157299,
19
  "auxillary_file_paths": [
20
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.pt"
21
  ]
22
  }
23
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.909090909090908,
8
+ "creation_time": 1679319009.9340475,
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": 19.636363636363637,
17
+ "creation_time": 1679319126.0108728,
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": 22.727272727272727,
26
+ "creation_time": 1679319243.385648,
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": 26.09090909090909,
35
+ "creation_time": 1679319357.595583,
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": 26.09090909090909,
44
+ "creation_time": 1679319357.7939312,
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": 26.09090909090909,
54
+ "creation_time": 1679319357.7939312,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },