Hugging Face's logo

Pulting86
/
ML-Agents-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
Pulting86 commited on
Commit
33726f8
·
verified ·
1 Parent(s): 5e69502

initial commit

Browse files
Files changed (14) hide show
  1. SoccerTwos.onnx +2 -2
  2. SoccerTwos/SoccerTwos-167966.onnx +3 -0
  3. SoccerTwos/SoccerTwos-167966.pt +3 -0
  4. SoccerTwos/SoccerTwos-65330.onnx +3 -0
  5. SoccerTwos/SoccerTwos-65330.pt +3 -0
  6. SoccerTwos/SoccerTwos-78306.onnx +3 -0
  7. SoccerTwos/SoccerTwos-78306.pt +3 -0
  8. SoccerTwos/checkpoint.pt +2 -2
  9. SoccerTwos/events.out.tfevents.1734649437.f653c7236a99.3891.0 +3 -0
  10. config.json +1 -1
  11. configuration.yaml +24 -24
  12. run_logs/Player-0.log +76 -14
  13. run_logs/timers.json +222 -152
  14. run_logs/training_status.json +9 -45
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:049673a0effbef8ebe84a03f0002cebcaa9c53f4d40349feccfc76e0f1654d1e
3
- size 1768747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb511c256e62d9eb6dbdd91a1597c91812a69a9ebad7b3a8230c50deb67ad035
3
+ size 9828907
SoccerTwos/SoccerTwos-167966.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb511c256e62d9eb6dbdd91a1597c91812a69a9ebad7b3a8230c50deb67ad035
3
+ size 9828907
SoccerTwos/SoccerTwos-167966.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25107ef8ca2856b9004cfa48139726531420d3726aa50f3f931becc9044b786
3
+ size 126068730
SoccerTwos/SoccerTwos-65330.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4f448358b0341bd08715420344ea5387e73805899e2feaf04cb1c370359abd
3
+ size 1768747
SoccerTwos/SoccerTwos-65330.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec5a13e2e87040fbf996e8a43c52d6ad4af4714659b6a4f46092efe1da97ff7
3
+ size 28430110
SoccerTwos/SoccerTwos-78306.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a762507112139b7f36fe17955859869b4847dc870685d5f6b923bd0ba42b5fe3
3
+ size 1768747
SoccerTwos/SoccerTwos-78306.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed06452f14bed8b70e264ca7d1d67244d8c5bba2de5af584012d7f1e2260b24d
3
+ size 10529636
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccce5910b99755d59b60e14eabb2a859eaeb57080ddfd0bd2f68ebafc99d9e0e
3
- size 28429366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f6ff687480a4547f9c8981f7c0f233eb794f9789fd69e9ef5f9b0cd4b261d7
3
+ size 126067666
SoccerTwos/events.out.tfevents.1734649437.f653c7236a99.3891.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dfca22620a7825286e5122873715cf7969f4a081fc7e8bb241f9e8f6752e9fa
3
+ size 165525
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "train-soccer/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwosNew", "initialize_from": null, "load_model": false, "resume": true, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 40960, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.15, "lambd": 0.92, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 1024, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 1200, "summary_freq": 5000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 300000, "swap_steps": 3000, "window": 20, "play_against_latest_model_ratio": 0.6, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "train-soccer/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwosNew", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,28 +3,28 @@ behaviors:
3
  SoccerTwos:
4
  trainer_type: poca
5
  hyperparameters:
6
- batch_size: 2048
7
- buffer_size: 20480
8
- learning_rate: 0.0003
9
- beta: 0.005
10
- epsilon: 0.2
11
- lambd: 0.95
12
- num_epoch: 3
13
- learning_rate_schedule: constant
14
- beta_schedule: constant
15
- epsilon_schedule: constant
16
  checkpoint_interval: 500000
17
  network_settings:
18
- normalize: false
19
- hidden_units: 512
20
- num_layers: 2
21
  vis_encode_type: simple
22
  memory: null
23
  goal_conditioning_type: hyper
24
  deterministic: false
25
  reward_signals:
26
  extrinsic:
27
- gamma: 0.99
28
  strength: 1.0
29
  network_settings:
30
  normalize: false
@@ -35,18 +35,18 @@ behaviors:
35
  goal_conditioning_type: hyper
36
  deterministic: false
37
  init_path: null
38
- keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 5000000
41
- time_horizon: 1000
42
- summary_freq: 10000
43
  threaded: false
44
  self_play:
45
  save_steps: 50000
46
- team_change: 200000
47
- swap_steps: 2000
48
- window: 10
49
- play_against_latest_model_ratio: 0.5
50
  initial_elo: 1200.0
51
  behavioral_cloning: null
52
  env_settings:
@@ -64,7 +64,7 @@ engine_settings:
64
  width: 84
65
  height: 84
66
  quality_level: 5
67
- time_scale: 20.0
68
  target_frame_rate: -1
69
  capture_frame_rate: 60
70
  no_graphics: true
@@ -74,7 +74,7 @@ checkpoint_settings:
74
  run_id: SoccerTwosNew
75
  initialize_from: null
76
  load_model: false
77
- resume: true
78
  force: true
79
  train_model: false
80
  inference: false
 
3
  SoccerTwos:
4
  trainer_type: poca
5
  hyperparameters:
6
+ batch_size: 4096
7
+ buffer_size: 40960
8
+ learning_rate: 0.0002
9
+ beta: 0.01
10
+ epsilon: 0.15
11
+ lambd: 0.92
12
+ num_epoch: 5
13
+ learning_rate_schedule: linear
14
+ beta_schedule: linear
15
+ epsilon_schedule: linear
16
  checkpoint_interval: 500000
17
  network_settings:
18
+ normalize: true
19
+ hidden_units: 1024
20
+ num_layers: 3
21
  vis_encode_type: simple
22
  memory: null
23
  goal_conditioning_type: hyper
24
  deterministic: false
25
  reward_signals:
26
  extrinsic:
27
+ gamma: 0.995
28
  strength: 1.0
29
  network_settings:
30
  normalize: false
 
35
  goal_conditioning_type: hyper
36
  deterministic: false
37
  init_path: null
38
+ keep_checkpoints: 10
39
  even_checkpoints: false
40
+ max_steps: 10000000
41
+ time_horizon: 1200
42
+ summary_freq: 5000
43
  threaded: false
44
  self_play:
45
  save_steps: 50000
46
+ team_change: 300000
47
+ swap_steps: 3000
48
+ window: 20
49
+ play_against_latest_model_ratio: 0.6
50
  initial_elo: 1200.0
51
  behavioral_cloning: null
52
  env_settings:
 
64
  width: 84
65
  height: 84
66
  quality_level: 5
67
+ time_scale: 20
68
  target_frame_rate: -1
69
  capture_frame_rate: 60
70
  no_graphics: true
 
74
  run_id: SoccerTwosNew
75
  initialize_from: null
76
  load_model: false
77
+ resume: false
78
  force: true
79
  train_model: false
80
  inference: false
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 0.309 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: 1.140572 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
@@ -64,12 +64,74 @@ TOO LONG
64
  TOO LONG
65
  TOO LONG
66
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  Setting up 1 worker threads for Enlighten.
68
  Memory Statistics:
69
  [ALLOC_TEMP_TLS] TLS Allocator
70
  StackAllocators :
71
  [ALLOC_TEMP_MAIN]
72
- Peak usage frame count: [8.0 KB-16.0 KB]: 347 frames, [2.0 MB-4.0 MB]: 1 frames
73
  Initial Block Size 4.0 MB
74
  Current Block Size 4.0 MB
75
  Peak Allocated Bytes 2.1 MB
@@ -185,22 +247,22 @@ Memory Statistics:
185
  Peak Allocated Bytes 0 B
186
  Overflow Count 0
187
  [ALLOC_DEFAULT] Dual Thread Allocator
188
- Peak main deferred allocation count 3
189
  [ALLOC_BUCKET]
190
  Large Block size 4.0 MB
191
  Used Block count 1
192
  Peak Allocated bytes 1.0 MB
193
  [ALLOC_DEFAULT_MAIN]
194
- Peak usage frame count: [4.0 MB-8.0 MB]: 348 frames
195
  Requested Block Size 16.0 MB
196
  Peak Block count 1
197
- Peak Allocated memory 4.7 MB
198
  Peak Large allocation bytes 0 B
199
  [ALLOC_DEFAULT_THREAD]
200
- Peak usage frame count: [16.0 MB-32.0 MB]: 348 frames
201
  Requested Block Size 16.0 MB
202
  Peak Block count 1
203
- Peak Allocated memory 17.5 MB
204
  Peak Large allocation bytes 16.0 MB
205
  [ALLOC_TEMP_JOB_1_FRAME]
206
  Initial Block Size 2.0 MB
@@ -229,13 +291,13 @@ Memory Statistics:
229
  Used Block count 1
230
  Peak Allocated bytes 1.0 MB
231
  [ALLOC_GFX_MAIN]
232
- Peak usage frame count: [32.0 KB-64.0 KB]: 347 frames, [64.0 KB-128.0 KB]: 1 frames
233
  Requested Block Size 16.0 MB
234
  Peak Block count 1
235
  Peak Allocated memory 65.6 KB
236
  Peak Large allocation bytes 0 B
237
  [ALLOC_GFX_THREAD]
238
- Peak usage frame count: [128.0 KB-256.0 KB]: 348 frames
239
  Requested Block Size 16.0 MB
240
  Peak Block count 1
241
  Peak Allocated memory 173.5 KB
@@ -247,13 +309,13 @@ Memory Statistics:
247
  Used Block count 1
248
  Peak Allocated bytes 1.0 MB
249
  [ALLOC_CACHEOBJECTS_MAIN]
250
- Peak usage frame count: [0.5 MB-1.0 MB]: 348 frames
251
  Requested Block Size 4.0 MB
252
  Peak Block count 1
253
  Peak Allocated memory 0.6 MB
254
  Peak Large allocation bytes 0 B
255
  [ALLOC_CACHEOBJECTS_THREAD]
256
- Peak usage frame count: [0.5 MB-1.0 MB]: 347 frames, [2.0 MB-4.0 MB]: 1 frames
257
  Requested Block Size 4.0 MB
258
  Peak Block count 1
259
  Peak Allocated memory 4.0 MB
@@ -265,13 +327,13 @@ Memory Statistics:
265
  Used Block count 1
266
  Peak Allocated bytes 1.0 MB
267
  [ALLOC_TYPETREE_MAIN]
268
- Peak usage frame count: [0-1.0 KB]: 348 frames
269
  Requested Block Size 2.0 MB
270
  Peak Block count 1
271
  Peak Allocated memory 1.0 KB
272
  Peak Large allocation bytes 0 B
273
  [ALLOC_TYPETREE_THREAD]
274
- Peak usage frame count: [1.0 KB-2.0 KB]: 347 frames, [2.0 KB-4.0 KB]: 1 frames
275
  Requested Block Size 2.0 MB
276
  Peak Block count 1
277
  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 0.112 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: 0.833949 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
 
64
  TOO LONG
65
  TOO LONG
66
  TOO LONG
67
+ TOO LONG
68
+ TOO LONG
69
+ TOO LONG
70
+ TOO LONG
71
+ TOO LONG
72
+ TOO LONG
73
+ TOO LONG
74
+ TOO LONG
75
+ TOO LONG
76
+ TOO LONG
77
+ TOO LONG
78
+ TOO LONG
79
+ TOO LONG
80
+ TOO LONG
81
+ TOO LONG
82
+ TOO LONG
83
+ TOO LONG
84
+ TOO LONG
85
+ TOO LONG
86
+ TOO LONG
87
+ TOO LONG
88
+ TOO LONG
89
+ TOO LONG
90
+ TOO LONG
91
+ TOO LONG
92
+ TOO LONG
93
+ TOO LONG
94
+ TOO LONG
95
+ TOO LONG
96
+ TOO LONG
97
+ TOO LONG
98
+ TOO LONG
99
+ TOO LONG
100
+ TOO LONG
101
+ TOO LONG
102
+ TOO LONG
103
+ TOO LONG
104
+ TOO LONG
105
+ TOO LONG
106
+ TOO LONG
107
+ TOO LONG
108
+ TOO LONG
109
+ TOO LONG
110
+ TOO LONG
111
+ TOO LONG
112
+ TOO LONG
113
+ TOO LONG
114
+ TOO LONG
115
+ TOO LONG
116
+ TOO LONG
117
+ TOO LONG
118
+ TOO LONG
119
+ TOO LONG
120
+ TOO LONG
121
+ TOO LONG
122
+ TOO LONG
123
+ TOO LONG
124
+ TOO LONG
125
+ TOO LONG
126
+ TOO LONG
127
+ TOO LONG
128
+ TOO LONG
129
  Setting up 1 worker threads for Enlighten.
130
  Memory Statistics:
131
  [ALLOC_TEMP_TLS] TLS Allocator
132
  StackAllocators :
133
  [ALLOC_TEMP_MAIN]
134
+ Peak usage frame count: [8.0 KB-16.0 KB]: 3248 frames, [2.0 MB-4.0 MB]: 1 frames
135
  Initial Block Size 4.0 MB
136
  Current Block Size 4.0 MB
137
  Peak Allocated Bytes 2.1 MB
 
247
  Peak Allocated Bytes 0 B
248
  Overflow Count 0
249
  [ALLOC_DEFAULT] Dual Thread Allocator
250
+ Peak main deferred allocation count 2
251
  [ALLOC_BUCKET]
252
  Large Block size 4.0 MB
253
  Used Block count 1
254
  Peak Allocated bytes 1.0 MB
255
  [ALLOC_DEFAULT_MAIN]
256
+ Peak usage frame count: [4.0 MB-8.0 MB]: 3249 frames
257
  Requested Block Size 16.0 MB
258
  Peak Block count 1
259
+ Peak Allocated memory 4.9 MB
260
  Peak Large allocation bytes 0 B
261
  [ALLOC_DEFAULT_THREAD]
262
+ Peak usage frame count: [16.0 MB-32.0 MB]: 3249 frames
263
  Requested Block Size 16.0 MB
264
  Peak Block count 1
265
+ Peak Allocated memory 17.4 MB
266
  Peak Large allocation bytes 16.0 MB
267
  [ALLOC_TEMP_JOB_1_FRAME]
268
  Initial Block Size 2.0 MB
 
291
  Used Block count 1
292
  Peak Allocated bytes 1.0 MB
293
  [ALLOC_GFX_MAIN]
294
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3248 frames, [64.0 KB-128.0 KB]: 1 frames
295
  Requested Block Size 16.0 MB
296
  Peak Block count 1
297
  Peak Allocated memory 65.6 KB
298
  Peak Large allocation bytes 0 B
299
  [ALLOC_GFX_THREAD]
300
+ Peak usage frame count: [128.0 KB-256.0 KB]: 3249 frames
301
  Requested Block Size 16.0 MB
302
  Peak Block count 1
303
  Peak Allocated memory 173.5 KB
 
309
  Used Block count 1
310
  Peak Allocated bytes 1.0 MB
311
  [ALLOC_CACHEOBJECTS_MAIN]
312
+ Peak usage frame count: [0.5 MB-1.0 MB]: 3249 frames
313
  Requested Block Size 4.0 MB
314
  Peak Block count 1
315
  Peak Allocated memory 0.6 MB
316
  Peak Large allocation bytes 0 B
317
  [ALLOC_CACHEOBJECTS_THREAD]
318
+ Peak usage frame count: [0.5 MB-1.0 MB]: 3248 frames, [2.0 MB-4.0 MB]: 1 frames
319
  Requested Block Size 4.0 MB
320
  Peak Block count 1
321
  Peak Allocated memory 4.0 MB
 
327
  Used Block count 1
328
  Peak Allocated bytes 1.0 MB
329
  [ALLOC_TYPETREE_MAIN]
330
+ Peak usage frame count: [0-1.0 KB]: 3249 frames
331
  Requested Block Size 2.0 MB
332
  Peak Block count 1
333
  Peak Allocated memory 1.0 KB
334
  Peak Large allocation bytes 0 B
335
  [ALLOC_TYPETREE_THREAD]
336
+ Peak usage frame count: [1.0 KB-2.0 KB]: 3248 frames, [2.0 KB-4.0 KB]: 1 frames
337
  Requested Block Size 2.0 MB
338
  Peak Block count 1
339
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,189 +2,261 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 3.1215877532958984,
6
- "min": 3.1215877532958984,
7
- "max": 3.1239140033721924,
8
- "count": 2
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 72021.2734375,
12
- "min": 27890.3046875,
13
- "max": 72021.2734375,
14
- "count": 2
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 791.8571428571429,
18
- "min": 250.5,
19
- "max": 791.8571428571429,
20
- "count": 2
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 22172.0,
24
- "min": 2004.0,
25
- "max": 22172.0,
26
- "count": 2
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1189.3699012116876,
30
- "min": 1188.5375790828034,
31
- "max": 1189.3699012116876,
32
- "count": 2
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 7136.219407270126,
36
- "min": 4754.150316331214,
37
- "max": 7136.219407270126,
38
- "count": 2
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 1939288.0,
42
- "min": 1929908.0,
43
- "max": 1939288.0,
44
- "count": 2
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 1939288.0,
48
- "min": 1929908.0,
49
- "max": 1939288.0,
50
- "count": 2
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.005367896985262632,
54
- "min": 0.0040137069299817085,
55
- "max": 0.005367896985262632,
56
- "count": 2
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 0.06978265941143036,
60
- "min": 0.012041120789945126,
61
- "max": 0.06978265941143036,
62
- "count": 2
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.005313304718583822,
66
- "min": 0.0037638049107044935,
67
- "max": 0.005313304718583822,
68
- "count": 2
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 0.06907296180725098,
72
- "min": 0.011291414499282837,
73
- "max": 0.06907296180725098,
74
- "count": 2
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 2
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 2
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": 0.06664615640273461,
90
- "min": -0.42640000581741333,
91
- "max": 0.06664615640273461,
92
- "count": 2
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": 0.8664000332355499,
96
- "min": -1.27920001745224,
97
- "max": 0.8664000332355499,
98
- "count": 2
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": 0.06664615640273461,
102
- "min": -0.42640000581741333,
103
- "max": 0.06664615640273461,
104
- "count": 2
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": 0.8664000332355499,
108
- "min": -1.27920001745224,
109
- "max": 0.8664000332355499,
110
- "count": 2
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 2
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  }
124
  },
125
  "metadata": {
126
  "timer_format_version": "0.1.0",
127
- "start_time_seconds": "1734598313",
128
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
129
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./results/SoccerTwosNew/configuration.yaml --env=train-soccer/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosNew --no-graphics --resume",
130
  "mlagents_version": "1.2.0.dev0",
131
  "mlagents_envs_version": "1.2.0.dev0",
132
  "communication_protocol_version": "1.5.0",
133
  "pytorch_version": "2.5.1+cu121",
134
  "numpy_version": "1.23.5",
135
- "end_time_seconds": "1734598367"
136
  },
137
- "total": 53.826016322000214,
138
  "count": 1,
139
- "self": 0.5316882900006021,
140
  "children": {
141
  "run_training.setup": {
142
- "total": 0.1335507290004898,
143
  "count": 1,
144
- "self": 0.1335507290004898
145
  },
146
  "TrainerController.start_learning": {
147
- "total": 53.16077730299912,
148
  "count": 1,
149
- "self": 0.04662201297651336,
150
  "children": {
151
  "TrainerController._reset_env": {
152
- "total": 3.7265824400001293,
153
- "count": 2,
154
- "self": 3.7265824400001293
155
  },
156
  "TrainerController.advance": {
157
- "total": 49.11176958402211,
158
- "count": 1164,
159
- "self": 0.06777152505674167,
160
  "children": {
161
  "env_step": {
162
- "total": 43.27889797501484,
163
- "count": 1164,
164
- "self": 34.79664238400801,
165
  "children": {
166
  "SubprocessEnvManager._take_step": {
167
- "total": 8.456765971019195,
168
- "count": 1164,
169
- "self": 0.3524788620434265,
170
  "children": {
171
  "TorchPolicy.evaluate": {
172
- "total": 8.104287108975768,
173
- "count": 2318,
174
- "self": 8.104287108975768
175
  }
176
  }
177
  },
178
  "workers": {
179
- "total": 0.025489619987638434,
180
- "count": 1163,
181
  "self": 0.0,
182
  "children": {
183
  "worker_root": {
184
- "total": 52.68498179995913,
185
- "count": 1163,
186
  "is_parallel": true,
187
- "self": 24.3567781089223,
188
  "children": {
189
  "run_training.setup": {
190
  "total": 0.0,
@@ -193,48 +265,48 @@
193
  "self": 0.0,
194
  "children": {
195
  "steps_from_proto": {
196
- "total": 0.0065249149993178435,
197
  "count": 2,
198
  "is_parallel": true,
199
- "self": 0.0019229169975005789,
200
  "children": {
201
  "_process_rank_one_or_two_observation": {
202
- "total": 0.004601998001817265,
203
  "count": 8,
204
  "is_parallel": true,
205
- "self": 0.004601998001817265
206
  }
207
  }
208
  },
209
  "UnityEnvironment.step": {
210
- "total": 0.05039826699976402,
211
  "count": 1,
212
  "is_parallel": true,
213
- "self": 0.0016422459993918892,
214
  "children": {
215
  "UnityEnvironment._generate_step_input": {
216
- "total": 0.0015098949988896493,
217
  "count": 1,
218
  "is_parallel": true,
219
- "self": 0.0015098949988896493
220
  },
221
  "communicator.exchange": {
222
- "total": 0.04249505000007048,
223
  "count": 1,
224
  "is_parallel": true,
225
- "self": 0.04249505000007048
226
  },
227
  "steps_from_proto": {
228
- "total": 0.004751076001412002,
229
  "count": 2,
230
  "is_parallel": true,
231
- "self": 0.0008594780010753311,
232
  "children": {
233
  "_process_rank_one_or_two_observation": {
234
- "total": 0.0038915980003366712,
235
  "count": 8,
236
  "is_parallel": true,
237
- "self": 0.0038915980003366712
238
  }
239
  }
240
  }
@@ -242,49 +314,35 @@
242
  }
243
  }
244
  },
245
- "steps_from_proto": {
246
- "total": 0.0025810010029090336,
247
- "count": 2,
248
- "is_parallel": true,
249
- "self": 0.0006256130054680398,
250
- "children": {
251
- "_process_rank_one_or_two_observation": {
252
- "total": 0.001955387997440994,
253
- "count": 8,
254
- "is_parallel": true,
255
- "self": 0.001955387997440994
256
- }
257
- }
258
- },
259
  "UnityEnvironment.step": {
260
- "total": 28.325622690033924,
261
- "count": 1162,
262
  "is_parallel": true,
263
- "self": 1.8417308320931625,
264
  "children": {
265
  "UnityEnvironment._generate_step_input": {
266
- "total": 1.305642324987275,
267
- "count": 1162,
268
  "is_parallel": true,
269
- "self": 1.305642324987275
270
  },
271
  "communicator.exchange": {
272
- "total": 19.552538940995873,
273
- "count": 1162,
274
  "is_parallel": true,
275
- "self": 19.552538940995873
276
  },
277
  "steps_from_proto": {
278
- "total": 5.625710591957613,
279
- "count": 2324,
280
  "is_parallel": true,
281
- "self": 1.0950379659770988,
282
  "children": {
283
  "_process_rank_one_or_two_observation": {
284
- "total": 4.530672625980515,
285
- "count": 9296,
286
  "is_parallel": true,
287
- "self": 4.530672625980515
288
  }
289
  }
290
  }
@@ -297,33 +355,45 @@
297
  }
298
  },
299
  "trainer_advance": {
300
- "total": 5.765100083950529,
301
- "count": 1163,
302
- "self": 0.22704366594734893,
303
  "children": {
304
  "process_trajectory": {
305
- "total": 5.53805641800318,
306
- "count": 1163,
307
- "self": 5.53805641800318
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  }
310
  }
311
  }
312
  },
313
  "trainer_threads": {
314
- "total": 1.7000002117129043e-06,
315
  "count": 1,
316
- "self": 1.7000002117129043e-06
317
  },
318
  "TrainerController._save_models": {
319
- "total": 0.2758015660001547,
320
  "count": 1,
321
- "self": 0.003718365000167978,
322
  "children": {
323
  "RLTrainer._checkpoint": {
324
- "total": 0.27208320099998673,
325
  "count": 1,
326
- "self": 0.27208320099998673
327
  }
328
  }
329
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.2580041885375977,
6
+ "min": 3.256819248199463,
7
+ "max": 3.2958016395568848,
8
+ "count": 32
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 25959.77734375,
12
+ "min": 7304.44970703125,
13
+ "max": 105465.65625,
14
+ "count": 32
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 804.6666666666666,
18
+ "min": 514.0,
19
+ "max": 999.0,
20
+ "count": 32
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 9656.0,
24
+ "min": 5164.0,
25
+ "max": 25456.0,
26
+ "count": 32
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1199.9918937200964,
30
+ "min": 1198.995732238514,
31
+ "max": 1202.735771789421,
32
+ "count": 23
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 4799.967574880386,
36
+ "min": 2397.991464477028,
37
+ "max": 7200.478516744472,
38
+ "count": 23
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 164312.0,
42
+ "min": 4744.0,
43
+ "max": 164312.0,
44
+ "count": 33
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 164312.0,
48
+ "min": 4744.0,
49
+ "max": 164312.0,
50
+ "count": 33
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.01650661788880825,
54
+ "min": 0.014312711544334888,
55
+ "max": 0.01822400651872158,
56
+ "count": 33
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.0990397110581398,
60
+ "min": 0.07246498018503189,
61
+ "max": 0.17305231094360352,
62
+ "count": 33
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.015817852690815926,
66
+ "min": 0.0140229482203722,
67
+ "max": 0.018223991617560387,
68
+ "count": 33
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.09490711241960526,
72
+ "min": 0.0707668885588646,
73
+ "max": 0.1779646873474121,
74
+ "count": 33
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 33
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 33
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.2533999979496002,
90
+ "min": -0.6666666666666666,
91
+ "max": 0.3553142717906407,
92
+ "count": 33
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -1.5203999876976013,
96
+ "min": -4.0,
97
+ "max": 2.487199902534485,
98
+ "count": 33
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.2533999979496002,
102
+ "min": -0.6666666666666666,
103
+ "max": 0.3553142717906407,
104
+ "count": 33
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -1.5203999876976013,
108
+ "min": -4.0,
109
+ "max": 2.487199902534485,
110
+ "count": 33
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 33
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 33
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.01186337743565673,
126
+ "min": 0.010897529197391122,
127
+ "max": 0.01186337743565673,
128
+ "count": 3
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01186337743565673,
132
+ "min": 0.010897529197391122,
133
+ "max": 0.01186337743565673,
134
+ "count": 3
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.0018270743754692377,
138
+ "min": 0.001220637378282845,
139
+ "max": 0.0018299973267130554,
140
+ "count": 3
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.0018270743754692377,
144
+ "min": 0.001220637378282845,
145
+ "max": 0.0018299973267130554,
146
+ "count": 3
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.0022152574150823058,
150
+ "min": 0.0012257124634925277,
151
+ "max": 0.0022152574150823058,
152
+ "count": 3
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.0022152574150823058,
156
+ "min": 0.0012257124634925277,
157
+ "max": 0.0022152574150823058,
158
+ "count": 3
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.00019747740126129998,
162
+ "min": 0.00019747740126129998,
163
+ "max": 0.00019916024041988003,
164
+ "count": 3
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.00019747740126129998,
168
+ "min": 0.00019747740126129998,
169
+ "max": 0.00019916024041988003,
170
+ "count": 3
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.14936934999999998,
174
+ "min": 0.14936934999999998,
175
+ "max": 0.14979005999999997,
176
+ "count": 3
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.14936934999999998,
180
+ "min": 0.14936934999999998,
181
+ "max": 0.14979005999999997,
182
+ "count": 3
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.00987399613,
186
+ "min": 0.00987399613,
187
+ "max": 0.009958053988000001,
188
+ "count": 3
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.00987399613,
192
+ "min": 0.00987399613,
193
+ "max": 0.009958053988000001,
194
+ "count": 3
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1734649436",
200
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
201
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./train-soccer/SoccerTwos.yaml --env=train-soccer/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosNew --no-graphics --force",
202
  "mlagents_version": "1.2.0.dev0",
203
  "mlagents_envs_version": "1.2.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.5.1+cu121",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1734652495"
208
  },
209
+ "total": 3058.635133326,
210
  "count": 1,
211
+ "self": 0.011386746999505704,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.07107127599999785,
215
  "count": 1,
216
+ "self": 0.07107127599999785
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 3058.5526753030003,
220
  "count": 1,
221
+ "self": 0.43878770101900955,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 2.6530812839999953,
225
+ "count": 1,
226
+ "self": 2.6530812839999953
227
  },
228
  "TrainerController.advance": {
229
+ "total": 3053.430203829981,
230
+ "count": 10885,
231
+ "self": 0.47846000396475574,
232
  "children": {
233
  "env_step": {
234
+ "total": 432.10954788101014,
235
+ "count": 10885,
236
+ "self": 301.1996523030123,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 130.65958004299125,
240
+ "count": 10885,
241
+ "self": 2.7501590370086433,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 127.90942100598261,
245
+ "count": 21654,
246
+ "self": 127.90942100598261
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.25031553500662085,
252
+ "count": 10885,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 2904.2377700600005,
257
+ "count": 10885,
258
  "is_parallel": true,
259
+ "self": 2655.7367181999834,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0036195470000848218,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0010192650000817594,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0026002820000030624,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.0026002820000030624
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.054792209999959596,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.001824118000058661,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.001034515000014835,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.001034515000014835
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.047184622000031595,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.047184622000031595
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.004748954999854504,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0007823239999424914,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.003966630999912013,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.003966630999912013
310
  }
311
  }
312
  }
 
314
  }
315
  }
316
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  "UnityEnvironment.step": {
318
+ "total": 248.50105186001701,
319
+ "count": 10884,
320
  "is_parallel": true,
321
+ "self": 15.532492222001792,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 10.477288217003206,
325
+ "count": 10884,
326
  "is_parallel": true,
327
+ "self": 10.477288217003206
328
  },
329
  "communicator.exchange": {
330
+ "total": 174.97494286499534,
331
+ "count": 10884,
332
  "is_parallel": true,
333
+ "self": 174.97494286499534
334
  },
335
  "steps_from_proto": {
336
+ "total": 47.516328556016674,
337
+ "count": 21768,
338
  "is_parallel": true,
339
+ "self": 8.244060707044355,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 39.27226784897232,
343
+ "count": 87072,
344
  "is_parallel": true,
345
+ "self": 39.27226784897232
346
  }
347
  }
348
  }
 
355
  }
356
  },
357
  "trainer_advance": {
358
+ "total": 2620.842195945006,
359
+ "count": 10885,
360
+ "self": 3.075410431014461,
361
  "children": {
362
  "process_trajectory": {
363
+ "total": 186.38785183599225,
364
+ "count": 10885,
365
+ "self": 186.38785183599225
366
+ },
367
+ "_update_policy": {
368
+ "total": 2431.3789336779996,
369
+ "count": 4,
370
+ "self": 48.15287891499975,
371
+ "children": {
372
+ "TorchPOCAOptimizer.update": {
373
+ "total": 2383.226054763,
374
+ "count": 160,
375
+ "self": 2383.226054763
376
+ }
377
+ }
378
  }
379
  }
380
  }
381
  }
382
  },
383
  "trainer_threads": {
384
+ "total": 1.8089999684889335e-06,
385
  "count": 1,
386
+ "self": 1.8089999684889335e-06
387
  },
388
  "TrainerController._save_models": {
389
+ "total": 2.0306006790001447,
390
  "count": 1,
391
+ "self": 0.9565477150003971,
392
  "children": {
393
  "RLTrainer._checkpoint": {
394
+ "total": 1.0740529639997476,
395
  "count": 1,
396
+ "self": 1.0740529639997476
397
  }
398
  }
399
  }
run_logs/training_status.json CHANGED
@@ -1,60 +1,24 @@
1
  {
2
  "SoccerTwos": {
 
3
  "checkpoints": [
4
  {
5
- "steps": 499956,
6
- "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-499956.onnx",
7
- "reward": 0.0,
8
- "creation_time": 1734589256.7309835,
9
- "auxillary_file_paths": [
10
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-499956.pt"
11
- ]
12
- },
13
- {
14
- "steps": 999700,
15
- "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-999700.onnx",
16
- "reward": 0.0,
17
- "creation_time": 1734592083.4013567,
18
- "auxillary_file_paths": [
19
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-999700.pt"
20
- ]
21
- },
22
- {
23
- "steps": 1499902,
24
- "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1499902.onnx",
25
- "reward": 0.0,
26
- "creation_time": 1734594948.3253822,
27
- "auxillary_file_paths": [
28
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1499902.pt"
29
- ]
30
- },
31
- {
32
- "steps": 1929180,
33
- "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1929180.onnx",
34
  "reward": null,
35
- "creation_time": 1734597453.4867852,
36
- "auxillary_file_paths": [
37
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1929180.pt"
38
- ]
39
- },
40
- {
41
- "steps": 1941340,
42
- "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1941340.onnx",
43
- "reward": 0.0,
44
- "creation_time": 1734598367.0981631,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1941340.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1190.0332015152508,
51
  "final_checkpoint": {
52
- "steps": 1941340,
53
  "file_path": "results/SoccerTwosNew/SoccerTwos.onnx",
54
- "reward": 0.0,
55
- "creation_time": 1734598367.0981631,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-1941340.pt"
58
  ]
59
  }
60
  },
 
1
  {
2
  "SoccerTwos": {
3
+ "elo": 1199.9918937200964,
4
  "checkpoints": [
5
  {
6
+ "steps": 167966,
7
+ "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-167966.onnx",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "reward": null,
9
+ "creation_time": 1734652494.0563092,
 
 
 
 
 
 
 
 
 
10
  "auxillary_file_paths": [
11
+ "results/SoccerTwosNew/SoccerTwos/SoccerTwos-167966.pt"
12
  ]
13
  }
14
  ],
 
15
  "final_checkpoint": {
16
+ "steps": 167966,
17
  "file_path": "results/SoccerTwosNew/SoccerTwos.onnx",
18
+ "reward": null,
19
+ "creation_time": 1734652494.0563092,
20
  "auxillary_file_paths": [
21
+ "results/SoccerTwosNew/SoccerTwos/SoccerTwos-167966.pt"
22
  ]
23
  }
24
  },