Hugging Face's logo

adrian-nf
/
ML-Agents-SoccerTwos-Bad

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
adrian-nf commited on
Commit
32e8f88
•
1 Parent(s): c71e117

Agent training resumed from the checkpoint.

Browse files
Files changed (10) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-62706.onnx +3 -0
  3. SoccerTwos/SoccerTwos-62706.pt +3 -0
  4. SoccerTwos/checkpoint.pt +1 -1
  5. SoccerTwos/events.out.tfevents.1734349455.27e73ea84d89.1006.0 +3 -0
  6. config.json +1 -1
  7. configuration.yaml +2 -2
  8. run_logs/Player-0.log +16 -20
  9. run_logs/timers.json +122 -194
  10. run_logs/training_status.json +14 -5
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa14a554dc243359c611edc61b507cfbe090be61e0b21a9b78badee70ff2ef5
3
  size 1768747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb90393f0daa23837236b71c41bcefef312b0d72ec7513cdf2970ab0075f7cc
3
  size 1768747
SoccerTwos/SoccerTwos-62706.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb90393f0daa23837236b71c41bcefef312b0d72ec7513cdf2970ab0075f7cc
3
+ size 1768747
SoccerTwos/SoccerTwos-62706.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1563a90bcaaef590f20710c33d8e7562b79b496d9a530ab68996f79f7a3d4c3e
3
+ size 28430110
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eed1f8a82c4c8d76b1b8461e4bc9a6b624c9a30ee962cb6e6f3976fde9edabf
3
  size 28429366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139243f02946be512a3cc41298a01b49b38338c7985ee27ae33d24b90c0598c3
3
  size 28429366
SoccerTwos/events.out.tfevents.1734349455.27e73ea84d89.1006.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e549e3f41fa939f520967180b69f7f38c4287974ba7c5071dc8cccbb4b0cc820
3
+ size 22050
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, "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}
 
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}
configuration.yaml CHANGED
@@ -64,7 +64,7 @@ engine_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
@@ -74,7 +74,7 @@ checkpoint_settings:
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
 
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
  run_id: SoccerTwosNew
75
  initialize_from: null
76
  load_model: false
77
+ resume: true
78
  force: true
79
  train_model: false
80
  inference: false
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.182 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)
@@ -59,7 +59,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
59
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
60
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
61
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
62
- UnloadTime: 1.008127 ms
63
  Registered Communicator in Agent.
64
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
65
  requesting resize 84 x 84
@@ -74,16 +74,12 @@ TOO LONG
74
  TOO LONG
75
  TOO LONG
76
  TOO LONG
77
- TOO LONG
78
- TOO LONG
79
- TOO LONG
80
- TOO LONG
81
  Setting up 1 worker threads for Enlighten.
82
  Memory Statistics:
83
  [ALLOC_TEMP_TLS] TLS Allocator
84
  StackAllocators :
85
  [ALLOC_TEMP_MAIN]
86
- Peak usage frame count: [8.0 KB-16.0 KB]: 862 frames, [2.0 MB-4.0 MB]: 1 frames
87
  Initial Block Size 4.0 MB
88
  Current Block Size 4.0 MB
89
  Peak Allocated Bytes 2.1 MB
@@ -199,23 +195,23 @@ Memory Statistics:
199
  Peak Allocated Bytes 0 B
200
  Overflow Count 0
201
  [ALLOC_DEFAULT] Dual Thread Allocator
202
- Peak main deferred allocation count 4
203
  [ALLOC_BUCKET]
204
  Large Block size 4.0 MB
205
  Used Block count 1
206
  Peak Allocated bytes 1.0 MB
207
  [ALLOC_DEFAULT_MAIN]
208
- Peak usage frame count: [4.0 MB-8.0 MB]: 863 frames
209
  Requested Block Size 16.0 MB
210
  Peak Block count 1
211
- Peak Allocated memory 5.0 MB
212
- Peak Large allocation bytes 0 B
213
  [ALLOC_DEFAULT_THREAD]
214
- Peak usage frame count: [16.0 MB-32.0 MB]: 863 frames
215
  Requested Block Size 16.0 MB
216
  Peak Block count 1
217
- Peak Allocated memory 17.2 MB
218
- Peak Large allocation bytes 16.0 MB
219
  [ALLOC_TEMP_JOB_1_FRAME]
220
  Initial Block Size 2.0 MB
221
  Used Block Count 1
@@ -243,13 +239,13 @@ Memory Statistics:
243
  Used Block count 1
244
  Peak Allocated bytes 1.0 MB
245
  [ALLOC_GFX_MAIN]
246
- Peak usage frame count: [32.0 KB-64.0 KB]: 862 frames, [64.0 KB-128.0 KB]: 1 frames
247
  Requested Block Size 16.0 MB
248
  Peak Block count 1
249
  Peak Allocated memory 65.6 KB
250
  Peak Large allocation bytes 0 B
251
  [ALLOC_GFX_THREAD]
252
- Peak usage frame count: [128.0 KB-256.0 KB]: 863 frames
253
  Requested Block Size 16.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 173.5 KB
@@ -261,13 +257,13 @@ Memory Statistics:
261
  Used Block count 1
262
  Peak Allocated bytes 1.0 MB
263
  [ALLOC_CACHEOBJECTS_MAIN]
264
- Peak usage frame count: [0.5 MB-1.0 MB]: 863 frames
265
  Requested Block Size 4.0 MB
266
  Peak Block count 1
267
  Peak Allocated memory 0.6 MB
268
  Peak Large allocation bytes 0 B
269
  [ALLOC_CACHEOBJECTS_THREAD]
270
- Peak usage frame count: [0.5 MB-1.0 MB]: 862 frames, [4.0 MB-8.0 MB]: 1 frames
271
  Requested Block Size 4.0 MB
272
  Peak Block count 2
273
  Peak Allocated memory 4.5 MB
@@ -279,13 +275,13 @@ Memory Statistics:
279
  Used Block count 1
280
  Peak Allocated bytes 1.0 MB
281
  [ALLOC_TYPETREE_MAIN]
282
- Peak usage frame count: [0-1.0 KB]: 863 frames
283
  Requested Block Size 2.0 MB
284
  Peak Block count 1
285
  Peak Allocated memory 1.0 KB
286
  Peak Large allocation bytes 0 B
287
  [ALLOC_TYPETREE_THREAD]
288
- Peak usage frame count: [1.0 KB-2.0 KB]: 862 frames, [2.0 KB-4.0 KB]: 1 frames
289
  Requested Block Size 2.0 MB
290
  Peak Block count 1
291
  Peak Allocated memory 2.2 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 0.140 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)
 
59
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
60
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
61
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
62
+ UnloadTime: 1.010630 ms
63
  Registered Communicator in Agent.
64
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
65
  requesting resize 84 x 84
 
74
  TOO LONG
75
  TOO LONG
76
  TOO LONG
 
 
 
 
77
  Setting up 1 worker threads for Enlighten.
78
  Memory Statistics:
79
  [ALLOC_TEMP_TLS] TLS Allocator
80
  StackAllocators :
81
  [ALLOC_TEMP_MAIN]
82
+ Peak usage frame count: [8.0 KB-16.0 KB]: 599 frames, [2.0 MB-4.0 MB]: 1 frames
83
  Initial Block Size 4.0 MB
84
  Current Block Size 4.0 MB
85
  Peak Allocated Bytes 2.1 MB
 
195
  Peak Allocated Bytes 0 B
196
  Overflow Count 0
197
  [ALLOC_DEFAULT] Dual Thread Allocator
198
+ Peak main deferred allocation count 2
199
  [ALLOC_BUCKET]
200
  Large Block size 4.0 MB
201
  Used Block count 1
202
  Peak Allocated bytes 1.0 MB
203
  [ALLOC_DEFAULT_MAIN]
204
+ Peak usage frame count: [16.0 MB-32.0 MB]: 600 frames
205
  Requested Block Size 16.0 MB
206
  Peak Block count 1
207
+ Peak Allocated memory 20.6 MB
208
+ Peak Large allocation bytes 16.0 MB
209
  [ALLOC_DEFAULT_THREAD]
210
+ Peak usage frame count: [1.0 MB-2.0 MB]: 600 frames
211
  Requested Block Size 16.0 MB
212
  Peak Block count 1
213
+ Peak Allocated memory 1.6 MB
214
+ Peak Large allocation bytes 0 B
215
  [ALLOC_TEMP_JOB_1_FRAME]
216
  Initial Block Size 2.0 MB
217
  Used Block Count 1
 
239
  Used Block count 1
240
  Peak Allocated bytes 1.0 MB
241
  [ALLOC_GFX_MAIN]
242
+ Peak usage frame count: [32.0 KB-64.0 KB]: 599 frames, [64.0 KB-128.0 KB]: 1 frames
243
  Requested Block Size 16.0 MB
244
  Peak Block count 1
245
  Peak Allocated memory 65.6 KB
246
  Peak Large allocation bytes 0 B
247
  [ALLOC_GFX_THREAD]
248
+ Peak usage frame count: [128.0 KB-256.0 KB]: 600 frames
249
  Requested Block Size 16.0 MB
250
  Peak Block count 1
251
  Peak Allocated memory 173.5 KB
 
257
  Used Block count 1
258
  Peak Allocated bytes 1.0 MB
259
  [ALLOC_CACHEOBJECTS_MAIN]
260
+ Peak usage frame count: [0.5 MB-1.0 MB]: 600 frames
261
  Requested Block Size 4.0 MB
262
  Peak Block count 1
263
  Peak Allocated memory 0.6 MB
264
  Peak Large allocation bytes 0 B
265
  [ALLOC_CACHEOBJECTS_THREAD]
266
+ Peak usage frame count: [0.5 MB-1.0 MB]: 599 frames, [4.0 MB-8.0 MB]: 1 frames
267
  Requested Block Size 4.0 MB
268
  Peak Block count 2
269
  Peak Allocated memory 4.5 MB
 
275
  Used Block count 1
276
  Peak Allocated bytes 1.0 MB
277
  [ALLOC_TYPETREE_MAIN]
278
+ Peak usage frame count: [0-1.0 KB]: 600 frames
279
  Requested Block Size 2.0 MB
280
  Peak Block count 1
281
  Peak Allocated memory 1.0 KB
282
  Peak Large allocation bytes 0 B
283
  [ALLOC_TYPETREE_THREAD]
284
+ Peak usage frame count: [1.0 KB-2.0 KB]: 599 frames, [2.0 KB-4.0 KB]: 1 frames
285
  Requested Block Size 2.0 MB
286
  Peak Block count 1
287
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,75 +2,75 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 3.2877609729766846,
6
- "min": 3.2877609729766846,
7
- "max": 3.295677423477173,
8
  "count": 3
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 30826.046875,
12
- "min": 30826.046875,
13
- "max": 105461.671875,
14
  "count": 3
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 853.8333333333334,
18
- "min": 720.75,
19
- "max": 853.8333333333334,
20
  "count": 3
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 20492.0,
24
- "min": 11532.0,
25
- "max": 29028.0,
26
  "count": 3
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1199.766521498713,
30
- "min": 1198.5058105483415,
31
- "max": 1200.0797527907453,
32
  "count": 3
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 2399.533042997426,
36
- "min": 2399.533042997426,
37
- "max": 7200.478516744472,
38
  "count": 3
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 29564.0,
42
- "min": 9532.0,
43
- "max": 29564.0,
44
  "count": 3
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 29564.0,
48
- "min": 9532.0,
49
- "max": 29564.0,
50
  "count": 3
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.027038216590881348,
54
- "min": 0.027038216590881348,
55
- "max": 0.02888910286128521,
56
  "count": 3
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 0.32445859909057617,
60
- "min": 0.32445859909057617,
61
- "max": 0.37555834650993347,
62
  "count": 3
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.025543570518493652,
66
- "min": 0.025543570518493652,
67
- "max": 0.028869880363345146,
68
  "count": 3
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 0.30652284622192383,
72
- "min": 0.30652284622192383,
73
- "max": 0.37530845403671265,
74
  "count": 3
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
86
  "count": 3
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": 0.14526666204134622,
90
- "min": -0.18960000001467192,
91
- "max": 0.14526666204134622,
92
  "count": 3
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": 1.7431999444961548,
96
- "min": -2.464800000190735,
97
- "max": 1.7431999444961548,
98
  "count": 3
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": 0.14526666204134622,
102
- "min": -0.18960000001467192,
103
- "max": 0.14526666204134622,
104
  "count": 3
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": 1.7431999444961548,
108
- "min": -2.464800000190735,
109
- "max": 1.7431999444961548,
110
  "count": 3
111
  },
112
  "SoccerTwos.IsTraining.mean": {
@@ -120,143 +120,71 @@
120
  "min": 1.0,
121
  "max": 1.0,
122
  "count": 3
123
- },
124
- "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.014585809665265678,
126
- "min": 0.014585809665265678,
127
- "max": 0.014585809665265678,
128
- "count": 1
129
- },
130
- "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.014585809665265678,
132
- "min": 0.014585809665265678,
133
- "max": 0.014585809665265678,
134
- "count": 1
135
- },
136
- "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.00283233120959873,
138
- "min": 0.00283233120959873,
139
- "max": 0.00283233120959873,
140
- "count": 1
141
- },
142
- "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.00283233120959873,
144
- "min": 0.00283233120959873,
145
- "max": 0.00283233120959873,
146
- "count": 1
147
- },
148
- "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.0025416993885301054,
150
- "min": 0.0025416993885301054,
151
- "max": 0.0025416993885301054,
152
- "count": 1
153
- },
154
- "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.0025416993885301054,
156
- "min": 0.0025416993885301054,
157
- "max": 0.0025416993885301054,
158
- "count": 1
159
- },
160
- "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 0.0003,
162
- "min": 0.0003,
163
- "max": 0.0003,
164
- "count": 1
165
- },
166
- "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 0.0003,
168
- "min": 0.0003,
169
- "max": 0.0003,
170
- "count": 1
171
- },
172
- "SoccerTwos.Policy.Epsilon.mean": {
173
- "value": 0.20000000000000004,
174
- "min": 0.20000000000000004,
175
- "max": 0.20000000000000004,
176
- "count": 1
177
- },
178
- "SoccerTwos.Policy.Epsilon.sum": {
179
- "value": 0.20000000000000004,
180
- "min": 0.20000000000000004,
181
- "max": 0.20000000000000004,
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": "1734342142",
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": "1734342346"
208
  },
209
- "total": 203.85273147499993,
210
  "count": 1,
211
- "self": 0.11239367799998945,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.11564643999986401,
215
  "count": 1,
216
- "self": 0.11564643999986401
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 203.62469135700007,
220
  "count": 1,
221
- "self": 0.12778788400055419,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 6.796155075000115,
225
  "count": 1,
226
- "self": 6.796155075000115
227
  },
228
  "TrainerController.advance": {
229
- "total": 196.33262598899955,
230
- "count": 2884,
231
- "self": 0.13600047201748566,
232
  "children": {
233
  "env_step": {
234
- "total": 101.80329289599149,
235
- "count": 2884,
236
- "self": 81.52352558299776,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 20.213718525989634,
240
- "count": 2884,
241
- "self": 0.7270953499773896,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 19.486623176012245,
245
- "count": 5752,
246
- "self": 19.486623176012245
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.06604878700409245,
252
- "count": 2883,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 202.97075250400394,
257
- "count": 2883,
258
  "is_parallel": true,
259
- "self": 135.7538479050006,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +193,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.004789489000131653,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.0014183030004915054,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.003371185999640147,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.003371185999640147
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.0482930519999627,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.0014633150001372996,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.001227130999950532,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.001227130999950532
292
  },
293
  "communicator.exchange": {
294
- "total": 0.041073415000028035,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.041073415000028035
298
  },
299
  "steps_from_proto": {
300
- "total": 0.004529190999846833,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.0007910709998668608,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.003738119999979972,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.003738119999979972
310
  }
311
  }
312
  }
@@ -315,34 +243,34 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 67.21690459900333,
319
- "count": 2882,
320
  "is_parallel": true,
321
- "self": 4.1035832000095525,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 2.7269875910005794,
325
- "count": 2882,
326
  "is_parallel": true,
327
- "self": 2.7269875910005794
328
  },
329
  "communicator.exchange": {
330
- "total": 47.56874020899909,
331
- "count": 2882,
332
  "is_parallel": true,
333
- "self": 47.56874020899909
334
  },
335
  "steps_from_proto": {
336
- "total": 12.817593598994108,
337
- "count": 5764,
338
  "is_parallel": true,
339
- "self": 2.229431004975595,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 10.588162594018513,
343
- "count": 23056,
344
  "is_parallel": true,
345
- "self": 10.588162594018513
346
  }
347
  }
348
  }
@@ -355,24 +283,24 @@
355
  }
356
  },
357
  "trainer_advance": {
358
- "total": 94.39333262099058,
359
- "count": 2883,
360
- "self": 0.6254764139919189,
361
  "children": {
362
  "process_trajectory": {
363
- "total": 17.527570402998663,
364
- "count": 2883,
365
- "self": 17.527570402998663
366
  },
367
  "_update_policy": {
368
- "total": 76.240285804,
369
  "count": 1,
370
- "self": 5.182799974000318,
371
  "children": {
372
  "TorchPOCAOptimizer.update": {
373
- "total": 71.05748582999968,
374
- "count": 39,
375
- "self": 71.05748582999968
376
  }
377
  }
378
  }
@@ -381,19 +309,19 @@
381
  }
382
  },
383
  "trainer_threads": {
384
- "total": 1.8069999896397348e-06,
385
  "count": 1,
386
- "self": 1.8069999896397348e-06
387
  },
388
  "TrainerController._save_models": {
389
- "total": 0.36812060199986263,
390
  "count": 1,
391
- "self": 0.0021252399999411864,
392
  "children": {
393
  "RLTrainer._checkpoint": {
394
- "total": 0.36599536199992144,
395
  "count": 1,
396
- "self": 0.36599536199992144
397
  }
398
  }
399
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.2813422679901123,
6
+ "min": 3.2797603607177734,
7
+ "max": 3.2813422679901123,
8
  "count": 3
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 69406.953125,
12
+ "min": 35578.83984375,
13
+ "max": 104975.2421875,
14
  "count": 3
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 984.5,
18
+ "min": 459.0,
19
+ "max": 984.5,
20
  "count": 3
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 23628.0,
24
+ "min": 3672.0,
25
+ "max": 28916.0,
26
  "count": 3
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1201.222288407967,
30
+ "min": 1201.222288407967,
31
+ "max": 1202.4914404208353,
32
  "count": 3
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 2402.444576815934,
36
+ "min": 2402.444576815934,
37
+ "max": 7209.071703418774,
38
  "count": 3
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 59706.0,
42
+ "min": 39040.0,
43
+ "max": 59706.0,
44
  "count": 3
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 59706.0,
48
+ "min": 39040.0,
49
+ "max": 59706.0,
50
  "count": 3
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.0251691285520792,
54
+ "min": 0.0251691285520792,
55
+ "max": 0.027628587558865547,
56
  "count": 3
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.27686041593551636,
60
+ "min": 0.21094191074371338,
61
+ "max": 0.33154305815696716,
62
  "count": 3
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.019476601853966713,
66
+ "min": 0.019476601853966713,
67
+ "max": 0.02308989316225052,
68
  "count": 3
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.214242622256279,
72
+ "min": 0.1697760671377182,
73
+ "max": 0.2770787179470062,
74
  "count": 3
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
 
86
  "count": 3
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.36363636363636365,
90
+ "min": -0.36363636363636365,
91
+ "max": 0.11886666218439738,
92
  "count": 3
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -4.0,
96
+ "min": -4.0,
97
+ "max": 1.4263999462127686,
98
  "count": 3
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.36363636363636365,
102
+ "min": -0.36363636363636365,
103
+ "max": 0.11886666218439738,
104
  "count": 3
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -4.0,
108
+ "min": -4.0,
109
+ "max": 1.4263999462127686,
110
  "count": 3
111
  },
112
  "SoccerTwos.IsTraining.mean": {
 
120
  "min": 1.0,
121
  "max": 1.0,
122
  "count": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  }
124
  },
125
  "metadata": {
126
  "timer_format_version": "0.1.0",
127
+ "start_time_seconds": "1734349453",
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": "1734349617"
136
  },
137
+ "total": 163.16620889400002,
138
  "count": 1,
139
+ "self": 0.009594704000022602,
140
  "children": {
141
  "run_training.setup": {
142
+ "total": 0.10617190499999651,
143
  "count": 1,
144
+ "self": 0.10617190499999651
145
  },
146
  "TrainerController.start_learning": {
147
+ "total": 163.050442285,
148
  "count": 1,
149
+ "self": 0.08201455699901317,
150
  "children": {
151
  "TrainerController._reset_env": {
152
+ "total": 6.299881440000007,
153
  "count": 1,
154
+ "self": 6.299881440000007
155
  },
156
  "TrainerController.advance": {
157
+ "total": 156.383009999001,
158
+ "count": 2004,
159
+ "self": 0.07024006500196833,
160
  "children": {
161
  "env_step": {
162
+ "total": 64.22660732399879,
163
+ "count": 2004,
164
+ "self": 52.391058236997,
165
  "children": {
166
  "SubprocessEnvManager._take_step": {
167
+ "total": 11.798904964001565,
168
+ "count": 2004,
169
+ "self": 0.38294599499960214,
170
  "children": {
171
  "TorchPolicy.evaluate": {
172
+ "total": 11.415958969001963,
173
+ "count": 4000,
174
+ "self": 11.415958969001963
175
  }
176
  }
177
  },
178
  "workers": {
179
+ "total": 0.036644123000229456,
180
+ "count": 2004,
181
  "self": 0.0,
182
  "children": {
183
  "worker_root": {
184
+ "total": 80.18677688799966,
185
+ "count": 2004,
186
  "is_parallel": true,
187
+ "self": 36.25111745799899,
188
  "children": {
189
  "run_training.setup": {
190
  "total": 0.0,
 
193
  "self": 0.0,
194
  "children": {
195
  "steps_from_proto": {
196
+ "total": 0.007672471999995878,
197
  "count": 2,
198
  "is_parallel": true,
199
+ "self": 0.0018231199999831915,
200
  "children": {
201
  "_process_rank_one_or_two_observation": {
202
+ "total": 0.005849352000012686,
203
  "count": 8,
204
  "is_parallel": true,
205
+ "self": 0.005849352000012686
206
  }
207
  }
208
  },
209
  "UnityEnvironment.step": {
210
+ "total": 0.0461561890000155,
211
  "count": 1,
212
  "is_parallel": true,
213
+ "self": 0.0013367729999913536,
214
  "children": {
215
  "UnityEnvironment._generate_step_input": {
216
+ "total": 0.0009743020000030356,
217
  "count": 1,
218
  "is_parallel": true,
219
+ "self": 0.0009743020000030356
220
  },
221
  "communicator.exchange": {
222
+ "total": 0.03982881500002122,
223
  "count": 1,
224
  "is_parallel": true,
225
+ "self": 0.03982881500002122
226
  },
227
  "steps_from_proto": {
228
+ "total": 0.00401629899999989,
229
  "count": 2,
230
  "is_parallel": true,
231
+ "self": 0.000687369999980092,
232
  "children": {
233
  "_process_rank_one_or_two_observation": {
234
+ "total": 0.003328929000019798,
235
  "count": 8,
236
  "is_parallel": true,
237
+ "self": 0.003328929000019798
238
  }
239
  }
240
  }
 
243
  }
244
  },
245
  "UnityEnvironment.step": {
246
+ "total": 43.93565943000067,
247
+ "count": 2003,
248
  "is_parallel": true,
249
+ "self": 2.6245066150007403,
250
  "children": {
251
  "UnityEnvironment._generate_step_input": {
252
+ "total": 1.7792221570002482,
253
+ "count": 2003,
254
  "is_parallel": true,
255
+ "self": 1.7792221570002482
256
  },
257
  "communicator.exchange": {
258
+ "total": 31.125804646999285,
259
+ "count": 2003,
260
  "is_parallel": true,
261
+ "self": 31.125804646999285
262
  },
263
  "steps_from_proto": {
264
+ "total": 8.406126011000396,
265
+ "count": 4006,
266
  "is_parallel": true,
267
+ "self": 1.4179039570013856,
268
  "children": {
269
  "_process_rank_one_or_two_observation": {
270
+ "total": 6.98822205399901,
271
+ "count": 16024,
272
  "is_parallel": true,
273
+ "self": 6.98822205399901
274
  }
275
  }
276
  }
 
283
  }
284
  },
285
  "trainer_advance": {
286
+ "total": 92.08616261000023,
287
+ "count": 2004,
288
+ "self": 0.3026151499994967,
289
  "children": {
290
  "process_trajectory": {
291
+ "total": 13.09741929400073,
292
+ "count": 2004,
293
+ "self": 13.09741929400073
294
  },
295
  "_update_policy": {
296
+ "total": 78.686128166,
297
  "count": 1,
298
+ "self": 5.072893774000022,
299
  "children": {
300
  "TorchPOCAOptimizer.update": {
301
+ "total": 73.61323439199998,
302
+ "count": 37,
303
+ "self": 73.61323439199998
304
  }
305
  }
306
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 1.5800000028320937e-06,
313
  "count": 1,
314
+ "self": 1.5800000028320937e-06
315
  },
316
  "TrainerController._save_models": {
317
+ "total": 0.28553470899998956,
318
  "count": 1,
319
+ "self": 0.0026438130000201454,
320
  "children": {
321
  "RLTrainer._checkpoint": {
322
+ "total": 0.2828908959999694,
323
  "count": 1,
324
+ "self": 0.2828908959999694
325
  }
326
  }
327
  }
run_logs/training_status.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 1200.017218281153,
4
  "checkpoints": [
5
  {
6
  "steps": 34564,
@@ -10,15 +10,24 @@
10
  "auxillary_file_paths": [
11
  "results/SoccerTwosNew/SoccerTwos/SoccerTwos-34564.pt"
12
  ]
 
 
 
 
 
 
 
 
 
13
  }
14
  ],
15
  "final_checkpoint": {
16
- "steps": 34564,
17
  "file_path": "results/SoccerTwosNew/SoccerTwos.onnx",
18
- "reward": 0.0,
19
- "creation_time": 1734342346.2948065,
20
  "auxillary_file_paths": [
21
- "results/SoccerTwosNew/SoccerTwos/SoccerTwos-34564.pt"
22
  ]
23
  }
24
  },
 
1
  {
2
  "SoccerTwos": {
3
+ "elo": 1200.9701914251082,
4
  "checkpoints": [
5
  {
6
  "steps": 34564,
 
10
  "auxillary_file_paths": [
11
  "results/SoccerTwosNew/SoccerTwos/SoccerTwos-34564.pt"
12
  ]
13
+ },
14
+ {
15
+ "steps": 62706,
16
+ "file_path": "results/SoccerTwosNew/SoccerTwos/SoccerTwos-62706.onnx",
17
+ "reward": null,
18
+ "creation_time": 1734349617.1518412,
19
+ "auxillary_file_paths": [
20
+ "results/SoccerTwosNew/SoccerTwos/SoccerTwos-62706.pt"
21
+ ]
22
  }
23
  ],
24
  "final_checkpoint": {
25
+ "steps": 62706,
26
  "file_path": "results/SoccerTwosNew/SoccerTwos.onnx",
27
+ "reward": null,
28
+ "creation_time": 1734349617.1518412,
29
  "auxillary_file_paths": [
30
+ "results/SoccerTwosNew/SoccerTwos/SoccerTwos-62706.pt"
31
  ]
32
  }
33
  },