Hugging Face's logo

manuu01
/
SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files
xet
Metrics Community
manuu01 commited on
Commit
7a55954
·
1 Parent(s): 66048fa

Update_agent

Browse files
Files changed (8) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-17041472.onnx +3 -0
  3. SoccerTwos/SoccerTwos-17041472.pt +3 -0
  4. SoccerTwos/checkpoint.pt +2 -2
  5. SoccerTwos/events.out.tfevents.1691502301.b7bdf8ec71f6.25795.0 +3 -0
  6. run_logs/Player-0.log +13 -13
  7. run_logs/timers.json +278 -72
  8. run_logs/training_status.json +28 -28
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:422acaf2aa96d5d8706b288df5ae2650414adb4c7ff634fe0ef922a2a74b26c2
3
  size 886472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e803f79f805fbc3cb4d6278d23ffa4ae72207083292f4af87098595ed4d9c0
3
  size 886472
SoccerTwos/SoccerTwos-17041472.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e803f79f805fbc3cb4d6278d23ffa4ae72207083292f4af87098595ed4d9c0
3
+ size 886472
SoccerTwos/SoccerTwos-17041472.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8db1a1c364ee4af5ad9e3ac010c675184080616a51cb700d650cffd644803d0
3
+ size 10303217
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f646e1848378913a7e673953a7de9b6c04882743a460c73ccdfa14541da2993
3
- size 3439277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8db1a1c364ee4af5ad9e3ac010c675184080616a51cb700d650cffd644803d0
3
+ size 10303217
SoccerTwos/events.out.tfevents.1691502301.b7bdf8ec71f6.25795.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0286d9b776325d7501d146d4e2c7ff7f4dcf3266e87d86589c03390b31e99e3d
3
+ size 42029
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.089 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -56,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
56
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
57
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
58
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
59
- UnloadTime: 0.886415 ms
60
  Registered Communicator in Agent.
61
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
62
  requesting resize 84 x 84
@@ -65,7 +65,7 @@ Memory Statistics:
65
  [ALLOC_TEMP_TLS] TLS Allocator
66
  StackAllocators :
67
  [ALLOC_TEMP_MAIN]
68
- Peak usage frame count: [2.0 KB-4.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 218 frames, [2.0 MB-4.0 MB]: 1 frames
69
  Initial Block Size 4.0 MB
70
  Current Block Size 4.0 MB
71
  Peak Allocated Bytes 2.1 MB
@@ -181,19 +181,19 @@ Memory Statistics:
181
  Peak Allocated Bytes 0 B
182
  Overflow Count 0
183
  [ALLOC_DEFAULT] Dual Thread Allocator
184
- Peak main deferred allocation count 2
185
  [ALLOC_BUCKET]
186
  Large Block size 4.0 MB
187
  Used Block count 1
188
  Peak Allocated bytes 1.0 MB
189
  [ALLOC_DEFAULT_MAIN]
190
- Peak usage frame count: [4.0 MB-8.0 MB]: 220 frames
191
  Requested Block Size 16.0 MB
192
  Peak Block count 1
193
  Peak Allocated memory 4.6 MB
194
  Peak Large allocation bytes 0 B
195
  [ALLOC_DEFAULT_THREAD]
196
- Peak usage frame count: [16.0 MB-32.0 MB]: 220 frames
197
  Requested Block Size 16.0 MB
198
  Peak Block count 1
199
  Peak Allocated memory 17.6 MB
@@ -225,13 +225,13 @@ Memory Statistics:
225
  Used Block count 1
226
  Peak Allocated bytes 1.0 MB
227
  [ALLOC_GFX_MAIN]
228
- Peak usage frame count: [32.0 KB-64.0 KB]: 219 frames, [64.0 KB-128.0 KB]: 1 frames
229
  Requested Block Size 16.0 MB
230
  Peak Block count 1
231
  Peak Allocated memory 65.6 KB
232
  Peak Large allocation bytes 0 B
233
  [ALLOC_GFX_THREAD]
234
- Peak usage frame count: [128.0 KB-256.0 KB]: 220 frames
235
  Requested Block Size 16.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 173.5 KB
@@ -243,16 +243,16 @@ Memory Statistics:
243
  Used Block count 1
244
  Peak Allocated bytes 1.0 MB
245
  [ALLOC_CACHEOBJECTS_MAIN]
246
- Peak usage frame count: [0.5 MB-1.0 MB]: 220 frames
247
  Requested Block Size 4.0 MB
248
  Peak Block count 1
249
  Peak Allocated memory 0.6 MB
250
  Peak Large allocation bytes 0 B
251
  [ALLOC_CACHEOBJECTS_THREAD]
252
- Peak usage frame count: [0.5 MB-1.0 MB]: 219 frames, [4.0 MB-8.0 MB]: 1 frames
253
  Requested Block Size 4.0 MB
254
  Peak Block count 2
255
- Peak Allocated memory 4.4 MB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE] Dual Thread Allocator
258
  Peak main deferred allocation count 0
@@ -261,13 +261,13 @@ Memory Statistics:
261
  Used Block count 1
262
  Peak Allocated bytes 1.0 MB
263
  [ALLOC_TYPETREE_MAIN]
264
- Peak usage frame count: [0-1.0 KB]: 220 frames
265
  Requested Block Size 2.0 MB
266
  Peak Block count 1
267
  Peak Allocated memory 1.0 KB
268
  Peak Large allocation bytes 0 B
269
  [ALLOC_TYPETREE_THREAD]
270
- Peak usage frame count: [1.0 KB-2.0 KB]: 219 frames, [2.0 KB-4.0 KB]: 1 frames
271
  Requested Block Size 2.0 MB
272
  Peak Block count 1
273
  Peak Allocated memory 2.2 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.110 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
56
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
57
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
58
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
59
+ UnloadTime: 0.855561 ms
60
  Registered Communicator in Agent.
61
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
62
  requesting resize 84 x 84
 
65
  [ALLOC_TEMP_TLS] TLS Allocator
66
  StackAllocators :
67
  [ALLOC_TEMP_MAIN]
68
+ Peak usage frame count: [8.0 KB-16.0 KB]: 779 frames, [2.0 MB-4.0 MB]: 1 frames
69
  Initial Block Size 4.0 MB
70
  Current Block Size 4.0 MB
71
  Peak Allocated Bytes 2.1 MB
 
181
  Peak Allocated Bytes 0 B
182
  Overflow Count 0
183
  [ALLOC_DEFAULT] Dual Thread Allocator
184
+ Peak main deferred allocation count 4
185
  [ALLOC_BUCKET]
186
  Large Block size 4.0 MB
187
  Used Block count 1
188
  Peak Allocated bytes 1.0 MB
189
  [ALLOC_DEFAULT_MAIN]
190
+ Peak usage frame count: [4.0 MB-8.0 MB]: 780 frames
191
  Requested Block Size 16.0 MB
192
  Peak Block count 1
193
  Peak Allocated memory 4.6 MB
194
  Peak Large allocation bytes 0 B
195
  [ALLOC_DEFAULT_THREAD]
196
+ Peak usage frame count: [16.0 MB-32.0 MB]: 780 frames
197
  Requested Block Size 16.0 MB
198
  Peak Block count 1
199
  Peak Allocated memory 17.6 MB
 
225
  Used Block count 1
226
  Peak Allocated bytes 1.0 MB
227
  [ALLOC_GFX_MAIN]
228
+ Peak usage frame count: [32.0 KB-64.0 KB]: 779 frames, [64.0 KB-128.0 KB]: 1 frames
229
  Requested Block Size 16.0 MB
230
  Peak Block count 1
231
  Peak Allocated memory 65.6 KB
232
  Peak Large allocation bytes 0 B
233
  [ALLOC_GFX_THREAD]
234
+ Peak usage frame count: [128.0 KB-256.0 KB]: 780 frames
235
  Requested Block Size 16.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 173.5 KB
 
243
  Used Block count 1
244
  Peak Allocated bytes 1.0 MB
245
  [ALLOC_CACHEOBJECTS_MAIN]
246
+ Peak usage frame count: [0.5 MB-1.0 MB]: 780 frames
247
  Requested Block Size 4.0 MB
248
  Peak Block count 1
249
  Peak Allocated memory 0.6 MB
250
  Peak Large allocation bytes 0 B
251
  [ALLOC_CACHEOBJECTS_THREAD]
252
+ Peak usage frame count: [0.5 MB-1.0 MB]: 779 frames, [4.0 MB-8.0 MB]: 1 frames
253
  Requested Block Size 4.0 MB
254
  Peak Block count 2
255
+ Peak Allocated memory 4.5 MB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE] Dual Thread Allocator
258
  Peak main deferred allocation count 0
 
261
  Used Block count 1
262
  Peak Allocated bytes 1.0 MB
263
  [ALLOC_TYPETREE_MAIN]
264
+ Peak usage frame count: [0-1.0 KB]: 780 frames
265
  Requested Block Size 2.0 MB
266
  Peak Block count 1
267
  Peak Allocated memory 1.0 KB
268
  Peak Large allocation bytes 0 B
269
  [ALLOC_TYPETREE_THREAD]
270
+ Peak usage frame count: [1.0 KB-2.0 KB]: 779 frames, [2.0 KB-4.0 KB]: 1 frames
271
  Requested Block Size 2.0 MB
272
  Peak Block count 1
273
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -1,8 +1,202 @@
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
- "start_time_seconds": "1691501860",
6
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
7
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
8
  "mlagents_version": "0.31.0.dev0",
@@ -10,59 +204,59 @@
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "1.11.0+cu102",
12
  "numpy_version": "1.21.2",
13
- "end_time_seconds": "1691501889"
14
  },
15
- "total": 28.53584493499966,
16
  "count": 1,
17
- "self": 0.3493573699997796,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.05527962900032435,
21
  "count": 1,
22
- "self": 0.05527962900032435
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 28.131207935999555,
26
  "count": 1,
27
- "self": 0.030626532991846034,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 1.1700617429987688,
31
  "count": 2,
32
- "self": 1.1700617429987688
33
  },
34
  "TrainerController.advance": {
35
- "total": 26.281978978009647,
36
- "count": 730,
37
- "self": 0.030869747054566687,
38
  "children": {
39
  "env_step": {
40
- "total": 26.061784669975168,
41
- "count": 730,
42
- "self": 22.065445951973743,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
- "total": 3.9798299469921403,
46
- "count": 730,
47
- "self": 0.16998933897320967,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
- "total": 3.8098406080189307,
51
- "count": 1460,
52
- "self": 3.8098406080189307
53
  }
54
  }
55
  },
56
  "workers": {
57
- "total": 0.01650877100928483,
58
- "count": 729,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
- "total": 27.1405192830116,
63
- "count": 729,
64
  "is_parallel": true,
65
- "self": 8.778881249988444,
66
  "children": {
67
  "run_training.setup": {
68
  "total": 0.0,
@@ -71,48 +265,48 @@
71
  "self": 0.0,
72
  "children": {
73
  "steps_from_proto": {
74
- "total": 0.0032415880004919018,
75
  "count": 2,
76
  "is_parallel": true,
77
- "self": 0.0008074170018517179,
78
  "children": {
79
  "_process_rank_one_or_two_observation": {
80
- "total": 0.002434170998640184,
81
  "count": 8,
82
  "is_parallel": true,
83
- "self": 0.002434170998640184
84
  }
85
  }
86
  },
87
  "UnityEnvironment.step": {
88
- "total": 0.05105509199984226,
89
  "count": 1,
90
  "is_parallel": true,
91
- "self": 0.001394826998875942,
92
  "children": {
93
  "UnityEnvironment._generate_step_input": {
94
- "total": 0.0009408830001120805,
95
  "count": 1,
96
  "is_parallel": true,
97
- "self": 0.0009408830001120805
98
  },
99
  "communicator.exchange": {
100
- "total": 0.04167974200026947,
101
  "count": 1,
102
  "is_parallel": true,
103
- "self": 0.04167974200026947
104
  },
105
  "steps_from_proto": {
106
- "total": 0.007039640000584768,
107
  "count": 2,
108
  "is_parallel": true,
109
- "self": 0.0008266439999715658,
110
  "children": {
111
  "_process_rank_one_or_two_observation": {
112
- "total": 0.006212996000613202,
113
  "count": 8,
114
  "is_parallel": true,
115
- "self": 0.006212996000613202
116
  }
117
  }
118
  }
@@ -121,48 +315,48 @@
121
  }
122
  },
123
  "steps_from_proto": {
124
- "total": 0.0022177380005814484,
125
  "count": 2,
126
  "is_parallel": true,
127
- "self": 0.0004237590019329218,
128
  "children": {
129
  "_process_rank_one_or_two_observation": {
130
- "total": 0.0017939789986485266,
131
  "count": 8,
132
  "is_parallel": true,
133
- "self": 0.0017939789986485266
134
  }
135
  }
136
  },
137
  "UnityEnvironment.step": {
138
- "total": 18.359420295022574,
139
- "count": 728,
140
  "is_parallel": true,
141
- "self": 1.0263596470167613,
142
  "children": {
143
  "UnityEnvironment._generate_step_input": {
144
- "total": 0.5398740819982777,
145
- "count": 728,
146
  "is_parallel": true,
147
- "self": 0.5398740819982777
148
  },
149
  "communicator.exchange": {
150
- "total": 13.557695215985405,
151
- "count": 728,
152
  "is_parallel": true,
153
- "self": 13.557695215985405
154
  },
155
  "steps_from_proto": {
156
- "total": 3.23549135002213,
157
- "count": 1456,
158
  "is_parallel": true,
159
- "self": 0.5434195109937718,
160
  "children": {
161
  "_process_rank_one_or_two_observation": {
162
- "total": 2.6920718390283582,
163
- "count": 5824,
164
  "is_parallel": true,
165
- "self": 2.6920718390283582
166
  }
167
  }
168
  }
@@ -175,33 +369,45 @@
175
  }
176
  },
177
  "trainer_advance": {
178
- "total": 0.18932456097991235,
179
- "count": 729,
180
- "self": 0.07149227297213656,
181
  "children": {
182
  "process_trajectory": {
183
- "total": 0.11783228800777579,
184
- "count": 729,
185
- "self": 0.11783228800777579
 
 
 
 
 
 
 
 
 
 
 
 
186
  }
187
  }
188
  }
189
  }
190
  },
191
  "trainer_threads": {
192
- "total": 1.8859991541830823e-06,
193
  "count": 1,
194
- "self": 1.8859991541830823e-06
195
  },
196
  "TrainerController._save_models": {
197
- "total": 0.648538796000139,
198
  "count": 1,
199
- "self": 0.0025338059995192452,
200
  "children": {
201
  "RLTrainer._checkpoint": {
202
- "total": 0.6460049900006197,
203
  "count": 1,
204
- "self": 0.6460049900006197
205
  }
206
  }
207
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.9639641046524048,
6
+ "min": 1.9539681673049927,
7
+ "max": 1.9984642267227173,
8
+ "count": 4
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 39719.2109375,
12
+ "min": 38954.30859375,
13
+ "max": 42015.7109375,
14
+ "count": 4
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 55.9080459770115,
18
+ "min": 52.42553191489362,
19
+ "max": 69.69117647058823,
20
+ "count": 4
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19456.0,
24
+ "min": 18956.0,
25
+ "max": 19736.0,
26
+ "count": 4
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1533.2775670474307,
30
+ "min": 1531.4690591729955,
31
+ "max": 1536.4409381825596,
32
+ "count": 4
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 266790.29666625295,
36
+ "min": 208780.49839865667,
37
+ "max": 288850.8963783212,
38
+ "count": 4
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 17039981.0,
42
+ "min": 17009985.0,
43
+ "max": 17039981.0,
44
+ "count": 4
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 17039981.0,
48
+ "min": 17009985.0,
49
+ "max": 17039981.0,
50
+ "count": 4
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.0066308374516665936,
54
+ "min": -0.014971102587878704,
55
+ "max": 0.007635193876922131,
56
+ "count": 4
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 1.1603965759277344,
60
+ "min": -2.8145673274993896,
61
+ "max": 1.2139958143234253,
62
+ "count": 4
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.004882545676082373,
66
+ "min": -0.015448137186467648,
67
+ "max": 0.008066718466579914,
68
+ "count": 4
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.8544454574584961,
72
+ "min": -2.849024772644043,
73
+ "max": 1.2826082706451416,
74
+ "count": 4
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 4
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 4
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.008789714404514858,
90
+ "min": -0.024712768323878025,
91
+ "max": 0.0715466645028856,
92
+ "count": 4
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -1.5382000207901,
96
+ "min": -4.646000444889069,
97
+ "max": 9.658799707889557,
98
+ "count": 4
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.008789714404514858,
102
+ "min": -0.024712768323878025,
103
+ "max": 0.0715466645028856,
104
+ "count": 4
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -1.5382000207901,
108
+ "min": -4.646000444889069,
109
+ "max": 9.658799707889557,
110
+ "count": 4
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 4
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 4
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.018175540817901494,
126
+ "min": 0.018175540817901494,
127
+ "max": 0.018175540817901494,
128
+ "count": 1
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.018175540817901494,
132
+ "min": 0.018175540817901494,
133
+ "max": 0.018175540817901494,
134
+ "count": 1
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.13336077183485032,
138
+ "min": 0.13336077183485032,
139
+ "max": 0.13336077183485032,
140
+ "count": 1
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.13336077183485032,
144
+ "min": 0.13336077183485032,
145
+ "max": 0.13336077183485032,
146
+ "count": 1
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.13435084397594135,
150
+ "min": 0.13435084397594135,
151
+ "max": 0.13435084397594135,
152
+ "count": 1
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.13435084397594135,
156
+ "min": 0.13435084397594135,
157
+ "max": 0.13435084397594135,
158
+ "count": 1
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.00019999999999999996,
162
+ "min": 0.00019999999999999996,
163
+ "max": 0.00019999999999999996,
164
+ "count": 1
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.00019999999999999996,
168
+ "min": 0.00019999999999999996,
169
+ "max": 0.00019999999999999996,
170
+ "count": 1
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 1
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 1
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 1
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 1
195
+ }
196
+ },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1691502300",
200
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
201
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
202
  "mlagents_version": "0.31.0.dev0",
 
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1691502467"
208
  },
209
+ "total": 167.2286620670002,
210
  "count": 1,
211
+ "self": 0.4083971010004461,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.057568434000131674,
215
  "count": 1,
216
+ "self": 0.057568434000131674
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 166.7626965319996,
220
  "count": 1,
221
+ "self": 0.1286187159948895,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 1.281048531000124,
225
  "count": 2,
226
+ "self": 1.281048531000124
227
  },
228
  "TrainerController.advance": {
229
+ "total": 164.82694835200527,
230
+ "count": 2866,
231
+ "self": 0.11029959502411657,
232
  "children": {
233
  "env_step": {
234
+ "total": 91.24394351102455,
235
+ "count": 2866,
236
+ "self": 77.27837632406408,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 13.897581628963053,
240
+ "count": 2866,
241
+ "self": 0.588474708949434,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 13.309106920013619,
245
+ "count": 5194,
246
+ "self": 13.309106920013619
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.06798555799741735,
252
+ "count": 2866,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 139.89436301402293,
257
+ "count": 2866,
258
  "is_parallel": true,
259
+ "self": 74.87586999501673,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.005311633000019356,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.001231124997502775,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.004080508002516581,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.004080508002516581
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.0493819719995372,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0013574589984273189,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0009895940002024872,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.0009895940002024872
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.04264585100008844,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.04264585100008844
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.004389068000818952,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0007751620014460059,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.003613905999372946,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.003613905999372946
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "steps_from_proto": {
318
+ "total": 0.0023167730005297926,
319
  "count": 2,
320
  "is_parallel": true,
321
+ "self": 0.00047645100130466744,
322
  "children": {
323
  "_process_rank_one_or_two_observation": {
324
+ "total": 0.0018403219992251252,
325
  "count": 8,
326
  "is_parallel": true,
327
+ "self": 0.0018403219992251252
328
  }
329
  }
330
  },
331
  "UnityEnvironment.step": {
332
+ "total": 65.01617624600567,
333
+ "count": 2865,
334
  "is_parallel": true,
335
+ "self": 3.78196505899723,
336
  "children": {
337
  "UnityEnvironment._generate_step_input": {
338
+ "total": 1.9756522910220156,
339
+ "count": 2865,
340
  "is_parallel": true,
341
+ "self": 1.9756522910220156
342
  },
343
  "communicator.exchange": {
344
+ "total": 47.213440500001525,
345
+ "count": 2865,
346
  "is_parallel": true,
347
+ "self": 47.213440500001525
348
  },
349
  "steps_from_proto": {
350
+ "total": 12.0451183959849,
351
+ "count": 5730,
352
  "is_parallel": true,
353
+ "self": 2.1130996969013722,
354
  "children": {
355
  "_process_rank_one_or_two_observation": {
356
+ "total": 9.932018699083528,
357
+ "count": 22920,
358
  "is_parallel": true,
359
+ "self": 9.932018699083528
360
  }
361
  }
362
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 73.4727052459566,
373
+ "count": 2866,
374
+ "self": 0.7132131789649065,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 14.632656675991711,
378
+ "count": 2866,
379
+ "self": 14.632656675991711
380
+ },
381
+ "_update_policy": {
382
+ "total": 58.126835390999986,
383
+ "count": 2,
384
+ "self": 10.704958797002291,
385
+ "children": {
386
+ "TorchPOCAOptimizer.update": {
387
+ "total": 47.421876593997695,
388
+ "count": 55,
389
+ "self": 47.421876593997695
390
+ }
391
+ }
392
  }
393
  }
394
  }
395
  }
396
  },
397
  "trainer_threads": {
398
+ "total": 2.1189998733461834e-06,
399
  "count": 1,
400
+ "self": 2.1189998733461834e-06
401
  },
402
  "TrainerController._save_models": {
403
+ "total": 0.5260788139994474,
404
  "count": 1,
405
+ "self": 0.007075401998918096,
406
  "children": {
407
  "RLTrainer._checkpoint": {
408
+ "total": 0.5190034120005294,
409
  "count": 1,
410
+ "self": 0.5190034120005294
411
  }
412
  }
413
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 17000414,
6
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17000414.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1691429992.5151367,
9
  "auxillary_file_paths": [
10
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17000414.pt"
11
  ]
12
  },
13
  {
14
- "steps": 17499624,
15
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17499624.onnx",
16
- "reward": null,
17
- "creation_time": 1691499298.6854486,
18
  "auxillary_file_paths": [
19
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17499624.pt"
20
  ]
21
  },
22
  {
23
- "steps": 17879860,
24
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17879860.onnx",
25
- "reward": null,
26
- "creation_time": 1691501511.1249673,
27
  "auxillary_file_paths": [
28
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17879860.pt"
29
  ]
30
  },
31
  {
32
- "steps": 17901730,
33
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17901730.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1691501697.695796,
36
  "auxillary_file_paths": [
37
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17901730.pt"
38
  ]
39
  },
40
  {
41
- "steps": 17902292,
42
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17902292.onnx",
43
- "reward": 0.0,
44
- "creation_time": 1691501888.896591,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17902292.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1535.1689542556592,
51
  "final_checkpoint": {
52
- "steps": 17902292,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
- "reward": 0.0,
55
- "creation_time": 1691501888.896591,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwos/SoccerTwos/SoccerTwos-17902292.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 16000076,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16000076.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1691424712.242151,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-16000076.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 16499968,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16499968.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1691428142.8108828,
18
  "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-16499968.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 16999840,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16999840.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1691429992.0673003,
27
  "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-16999840.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 17000414,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17000414.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1691429992.5151367,
36
  "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-17000414.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 17041472,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17041472.onnx",
43
+ "reward": null,
44
+ "creation_time": 1691502466.8981693,
45
  "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-17041472.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1536.6166151058592,
51
  "final_checkpoint": {
52
+ "steps": 17041472,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
+ "reward": null,
55
+ "creation_time": 1691502466.8981693,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-17041472.pt"
58
  ]
59
  }
60
  },