Hugging Face's logo

SAL83
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
SAL83 commited on
Commit
3535510
·
1 Parent(s): f4426df

First Push

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.pt +0 -3
  3. SnowballTarget/SnowballTarget-199984.onnx +0 -3
  4. SnowballTarget/SnowballTarget-199984.pt +0 -3
  5. SnowballTarget/SnowballTarget-200200.onnx +0 -3
  6. SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-41008.onnx} +1 -1
  7. SnowballTarget/{SnowballTarget-200200.pt → SnowballTarget-41008.pt} +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +0 -3
  9. SnowballTarget/SnowballTarget-49936.pt +0 -3
  10. SnowballTarget/SnowballTarget-99960.onnx +0 -3
  11. SnowballTarget/SnowballTarget-99960.pt +0 -3
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/{events.out.tfevents.1679525522.366b333c0ecb.2073.0 → events.out.tfevents.1679601315.afeaf6cfeead.1478.0} +2 -2
  14. run_logs/Player-0.log +15 -15
  15. run_logs/timers.json +151 -159
  16. run_logs/training_status.json +9 -45
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4c39319ca761afebf5c8d124ce88b81cb556733102a4569217744e5b490fca
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f4db036f754056a7778e2c12e73ad88a873b13ea994caae41c2b618ac857e3
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d552c98fed848f3f7d0cc7799aefd39308700b800d3c955a9ee50ab6b4f39a1
3
- size 3843200
 
 
 
 
SnowballTarget/SnowballTarget-199984.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4c39319ca761afebf5c8d124ce88b81cb556733102a4569217744e5b490fca
3
- size 646532
 
 
 
 
SnowballTarget/SnowballTarget-199984.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdac188437fc845779bdfaf02ed1c8ecc6c1c66d8371b3e6f19a55cd2598b9f1
3
- size 3843200
 
 
 
 
SnowballTarget/SnowballTarget-200200.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4c39319ca761afebf5c8d124ce88b81cb556733102a4569217744e5b490fca
3
- size 646532
 
 
 
 
SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-41008.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a634608eb1ae1e9769ce488f90fb16bda188618cb6c5507c314fe20a7560e03
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f4db036f754056a7778e2c12e73ad88a873b13ea994caae41c2b618ac857e3
3
  size 646532
SnowballTarget/{SnowballTarget-200200.pt → SnowballTarget-41008.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb607aa0e94faed37f71c7e4fe2bb28b0f4140fe5f15e4236024e0de39e5d34
3
  size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686e8b6d817e23ad7d652de16a32196dc7b776db86725b90b98353bb1852d9e9
3
  size 3843200
SnowballTarget/SnowballTarget-49936.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d84561b75e444fae687bacf722efa7793ef5e7d4851b53219fd7402cd6635351
3
- size 646532
 
 
 
 
SnowballTarget/SnowballTarget-49936.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eb5e8444e837a7f36a81c2d837345c577f141b07dc3928f3d01cf4677546cd9
3
- size 3843200
 
 
 
 
SnowballTarget/SnowballTarget-99960.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6812f3ba4ed4e2b810e921f88eac826bb8d4b183d02c2f755005b04985ef045b
3
- size 646532
 
 
 
 
SnowballTarget/SnowballTarget-99960.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea3a7328250a1328c3bb732f0b9236aecbabad4fcc1221e1e79a136fedb98c45
3
- size 3843200
 
 
 
 
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb607aa0e94faed37f71c7e4fe2bb28b0f4140fe5f15e4236024e0de39e5d34
3
  size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686e8b6d817e23ad7d652de16a32196dc7b776db86725b90b98353bb1852d9e9
3
  size 3843200
SnowballTarget/{events.out.tfevents.1679525522.366b333c0ecb.2073.0 → events.out.tfevents.1679601315.afeaf6cfeead.1478.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ae8f3603af74734e47d788309e90f73001d18f0919604261d6b905a21a060e2
3
- size 28363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8507eb64440cce202857e8b4f42abb510205aba660a948d0dec698058799c2
3
+ size 14733
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 0.105 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: 0.833368 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]: 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
@@ -169,22 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 36
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 6.6 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 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 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]: 4694 frames, [64.0 KB-128.0 KB]: 767 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
@@ -231,13 +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]: 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
@@ -249,13 +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]: 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
 
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 0.111 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: 0.981560 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]: 1114 frames, [16.0 KB-32.0 KB]: 18 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]: 1133 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 5.9 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 1133 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.4 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 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]: 901 frames, [64.0 KB-128.0 KB]: 232 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1133 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]: 1133 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]: 1132 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]: 1133 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]: 1133 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": 0.9586253762245178,
6
- "min": 0.9586253762245178,
7
- "max": 2.8641905784606934,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9174.044921875,
12
- "min": 9174.044921875,
13
- "max": 29458.19921875,
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": 12.535113334655762,
30
- "min": 0.40824639797210693,
31
- "max": 12.535113334655762,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2444.34716796875,
36
- "min": 79.19979858398438,
37
- "max": 2528.007080078125,
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": 0.07109583027982701,
54
- "min": 0.0625584123580826,
55
- "max": 0.07943687640320551,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.28438332111930803,
60
- "min": 0.2509329643930245,
61
- "max": 0.37091977750499017,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1906367755111526,
66
- "min": 0.11833749829412565,
67
- "max": 0.2810586610845491,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7625471020446104,
72
- "min": 0.4733499931765026,
73
- "max": 1.4052933054227454,
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": 25.15909090909091,
114
- "min": 3.227272727272727,
115
- "max": 25.15909090909091,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1107.0,
120
- "min": 142.0,
121
- "max": 1362.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.15909090909091,
126
- "min": 3.227272727272727,
127
- "max": 25.15909090909091,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1107.0,
132
- "min": 142.0,
133
- "max": 1362.0,
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": "1679525516",
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": "1679526072"
160
  },
161
- "total": 556.3675121939999,
162
  "count": 1,
163
- "self": 0.5403598019998981,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.12868620200003988,
167
  "count": 1,
168
- "self": 0.12868620200003988
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 555.69846619,
172
  "count": 1,
173
- "self": 0.8103461139945694,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 6.397031453000011,
177
  "count": 1,
178
- "self": 6.397031453000011
179
  },
180
  "TrainerController.advance": {
181
- "total": 548.3384897810056,
182
- "count": 18203,
183
- "self": 0.4381099980129193,
184
  "children": {
185
  "env_step": {
186
- "total": 547.9003797829927,
187
- "count": 18203,
188
- "self": 441.1587867260058,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 106.3423087139982,
192
- "count": 18203,
193
- "self": 2.9713236019977103,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 103.37098511200048,
197
- "count": 18203,
198
- "self": 103.37098511200048
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3992843429886648,
204
- "count": 18203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 553.6396466209958,
209
- "count": 18203,
210
  "is_parallel": true,
211
- "self": 241.0167414939919,
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": 0.006098663999978271,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004389518999857955,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0017091450001203157,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0017091450001203157
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.12214803599999868,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0009339129999261786,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00041699300004438555,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00041699300004438555
244
  },
245
  "communicator.exchange": {
246
- "total": 0.11830476300002601,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.11830476300002601
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0024923670000021048,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004958299999202609,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001996537000081844,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001996537000081844
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 312.6229051270039,
271
- "count": 18202,
272
  "is_parallel": true,
273
- "self": 12.152512487016566,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.7239914739964775,
277
- "count": 18202,
278
  "is_parallel": true,
279
- "self": 6.7239914739964775
280
  },
281
  "communicator.exchange": {
282
- "total": 251.98683416400172,
283
- "count": 18202,
284
  "is_parallel": true,
285
- "self": 251.98683416400172
286
  },
287
  "steps_from_proto": {
288
- "total": 41.759567001989126,
289
- "count": 18202,
290
  "is_parallel": true,
291
- "self": 8.643355341986478,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 33.11621166000265,
295
- "count": 182020,
296
  "is_parallel": true,
297
- "self": 33.11621166000265
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00023582399990118574,
313
  "count": 1,
314
- "self": 0.00023582399990118574,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,28 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 543.0088442899482,
324
- "count": 629411,
325
  "is_parallel": true,
326
- "self": 15.056491731946608,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 297.823841005001,
330
- "count": 629411,
331
  "is_parallel": true,
332
- "self": 296.538491940001,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 1.2853490649999912,
336
- "count": 4,
337
- "is_parallel": true,
338
- "self": 1.2853490649999912
339
- }
340
- }
341
  },
342
  "_update_policy": {
343
- "total": 230.12851155300058,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 82.81866688699984,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 147.30984466600074,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 147.30984466600074
353
  }
354
  }
355
  }
@@ -360,14 +352,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.15236301799996,
364
  "count": 1,
365
- "self": 0.0012170079999123118,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15114601000004768,
369
  "count": 1,
370
- "self": 0.15114601000004768
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.5011484622955322,
6
+ "min": 2.5011484622955322,
7
+ "max": 2.8680579662323,
8
+ "count": 4
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 25614.26171875,
12
+ "min": 25480.396484375,
13
+ "max": 29371.78125,
14
+ "count": 4
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 39984.0,
18
  "min": 9952.0,
19
+ "max": 39984.0,
20
+ "count": 4
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 39984.0,
24
  "min": 9952.0,
25
+ "max": 39984.0,
26
+ "count": 4
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 3.4007062911987305,
30
+ "min": 0.4964136779308319,
31
+ "max": 3.4007062911987305,
32
+ "count": 4
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 697.144775390625,
36
+ "min": 96.30425262451172,
37
+ "max": 697.144775390625,
38
+ "count": 4
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 4
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 4
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06724189642768846,
54
+ "min": 0.06545925535354792,
55
+ "max": 0.07198938031856704,
56
+ "count": 4
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3362094821384423,
60
+ "min": 0.2618370214141917,
61
+ "max": 0.3435879141658969,
62
+ "count": 4
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.26050749906137877,
66
+ "min": 0.12958442741621506,
67
+ "max": 0.26050749906137877,
68
+ "count": 4
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 1.3025374953068938,
72
+ "min": 0.5183377096648603,
73
+ "max": 1.3025374953068938,
74
+ "count": 4
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.000247332017556,
78
+ "min": 0.000247332017556,
79
  "max": 0.000291882002706,
80
+ "count": 4
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00123666008778,
84
+ "min": 0.001048728050424,
85
  "max": 0.00138516003828,
86
+ "count": 4
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.182444,
90
+ "min": 0.182444,
91
  "max": 0.19729400000000002,
92
+ "count": 4
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.91222,
96
+ "min": 0.7495760000000001,
97
  "max": 0.96172,
98
+ "count": 4
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0041239556000000005,
102
+ "min": 0.0041239556000000005,
103
  "max": 0.0048649706,
104
+ "count": 4
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.020619778000000002,
108
+ "min": 0.017483842399999998,
109
  "max": 0.023089828,
110
+ "count": 4
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 9.745454545454546,
114
+ "min": 3.6818181818181817,
115
+ "max": 9.745454545454546,
116
+ "count": 4
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 536.0,
120
+ "min": 162.0,
121
+ "max": 536.0,
122
+ "count": 4
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 9.745454545454546,
126
+ "min": 3.6818181818181817,
127
+ "max": 9.745454545454546,
128
+ "count": 4
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 536.0,
132
+ "min": 162.0,
133
+ "max": 536.0,
134
+ "count": 4
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 4
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 4
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1679601307",
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": "1679601420"
160
  },
161
+ "total": 113.13805195499998,
162
  "count": 1,
163
+ "self": 0.5925590929999203,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.14755938900003684,
167
  "count": 1,
168
+ "self": 0.14755938900003684
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 112.39793347300002,
172
  "count": 1,
173
+ "self": 0.18703768699856482,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 7.21208760799999,
177
  "count": 1,
178
+ "self": 7.21208760799999
179
  },
180
  "TrainerController.advance": {
181
+ "total": 104.74607768300149,
182
+ "count": 3776,
183
+ "self": 0.08626606600086006,
184
  "children": {
185
  "env_step": {
186
+ "total": 104.65981161700063,
187
+ "count": 3776,
188
+ "self": 83.79722994100138,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 20.777455623999174,
192
+ "count": 3776,
193
+ "self": 0.9765279589972238,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 19.80092766500195,
197
+ "count": 3776,
198
+ "self": 19.80092766500195
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.08512605200007783,
204
+ "count": 3775,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 111.79638906800318,
209
+ "count": 3775,
210
  "is_parallel": true,
211
+ "self": 53.29875949400298,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005979508999985228,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004350637000015922,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016288719999693058,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016288719999693058
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03412332900001047,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006725410000285592,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038394999995716717,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038394999995716717
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.031292018000044663,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.031292018000044663
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017748199999800818,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00038848000002644767,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001386339999953634,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001386339999953634
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 58.4976295740002,
271
+ "count": 3774,
272
  "is_parallel": true,
273
+ "self": 2.232591015992739,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 1.3561096210019628,
277
+ "count": 3774,
278
  "is_parallel": true,
279
+ "self": 1.3561096210019628
280
  },
281
  "communicator.exchange": {
282
+ "total": 47.766040094003756,
283
+ "count": 3774,
284
  "is_parallel": true,
285
+ "self": 47.766040094003756
286
  },
287
  "steps_from_proto": {
288
+ "total": 7.142888843001742,
289
+ "count": 3774,
290
  "is_parallel": true,
291
+ "self": 1.5731605450089319,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 5.56972829799281,
295
+ "count": 37740,
296
  "is_parallel": true,
297
+ "self": 5.56972829799281
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 5.043999999543303e-05,
313
  "count": 1,
314
+ "self": 5.043999999543303e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 104.00646663000742,
324
+ "count": 107463,
325
  "is_parallel": true,
326
+ "self": 2.2027032020147885,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 58.48694914299256,
330
+ "count": 107463,
331
  "is_parallel": true,
332
+ "self": 58.48694914299256
 
 
 
 
 
 
 
 
333
  },
334
  "_update_policy": {
335
+ "total": 43.31681428500008,
336
+ "count": 18,
337
  "is_parallel": true,
338
+ "self": 11.642654914999696,
339
  "children": {
340
  "TorchPPOOptimizer.update": {
341
+ "total": 31.674159370000382,
342
+ "count": 915,
343
  "is_parallel": true,
344
+ "self": 31.674159370000382
345
  }
346
  }
347
  }
 
352
  }
353
  },
354
  "TrainerController._save_models": {
355
+ "total": 0.2526800549999848,
356
  "count": 1,
357
+ "self": 0.0010210899999947287,
358
  "children": {
359
  "RLTrainer._checkpoint": {
360
+ "total": 0.2516589649999901,
361
  "count": 1,
362
+ "self": 0.2516589649999901
363
  }
364
  }
365
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,22 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.0,
8
- "creation_time": 1679525655.6487498,
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": 20.727272727272727,
17
- "creation_time": 1679525789.752794,
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": 23.454545454545453,
26
- "creation_time": 1679525922.2484217,
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": 25.363636363636363,
35
- "creation_time": 1679526072.0619273,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200200,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
- "reward": 24.727272727272727,
44
- "creation_time": 1679526072.2661488,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 24.727272727272727,
54
- "creation_time": 1679526072.2661488,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 41008,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-41008.onnx",
7
+ "reward": 10.727272727272727,
8
+ "creation_time": 1679601420.3565102,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-41008.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
+ "steps": 41008,
16
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
+ "reward": 10.727272727272727,
18
+ "creation_time": 1679601420.3565102,
19
  "auxillary_file_paths": [
20
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-41008.pt"
21
  ]
22
  }
23
  },