Hugging Face's logo

DContrerasF
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
DContrerasF commited on
Commit
931a870
•
1 Parent(s): ffe1605

Extended train

Browse files
Files changed (18) hide show
  1. SoccerTwos.onnx +2 -2
  2. SoccerTwos/SoccerTwos-10000052.onnx +3 -0
  3. SoccerTwos/SoccerTwos-10000052.pt +3 -0
  4. SoccerTwos/SoccerTwos-8499977.onnx +3 -0
  5. SoccerTwos/SoccerTwos-8499977.pt +3 -0
  6. SoccerTwos/SoccerTwos-8999972.onnx +3 -0
  7. SoccerTwos/SoccerTwos-8999972.pt +3 -0
  8. SoccerTwos/SoccerTwos-9499852.onnx +3 -0
  9. SoccerTwos/SoccerTwos-9499852.pt +3 -0
  10. SoccerTwos/SoccerTwos-9999968.onnx +3 -0
  11. SoccerTwos/SoccerTwos-9999968.pt +3 -0
  12. SoccerTwos/checkpoint.pt +2 -2
  13. SoccerTwos/events.out.tfevents.1700226013.dl-workstation.3599749.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +6 -6
  16. run_logs/Player-0.log +22 -72
  17. run_logs/timers.json +182 -182
  18. run_logs/training_status.json +25 -25
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510c202145c5ad8599e68cea6ed22d791a9b589f74cf9260ad62ddbdc451b904
3
- size 1768747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc800628b9ae195e43366fa3afb04a58a0c394396804b04af4b88696c863b58b
3
+ size 2820313
SoccerTwos/SoccerTwos-10000052.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc800628b9ae195e43366fa3afb04a58a0c394396804b04af4b88696c863b58b
3
+ size 2820313
SoccerTwos/SoccerTwos-10000052.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365de031ff08a7feffc0d9f30596784eb7dceb63a510c949f29d4d0eeaeac9b3
3
+ size 34741042
SoccerTwos/SoccerTwos-8499977.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2f1eb138142ec6ff7a6d2d5c414617505496c697015cc1e3c1bc288a2db3d3
3
+ size 2820313
SoccerTwos/SoccerTwos-8499977.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8445b0d6fb68cdc39a6c47e1b4dfc7e021f4b3b89a6f733ecb0ba02ef43e491
3
+ size 34740902
SoccerTwos/SoccerTwos-8999972.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f5513f10c3b80d3560feca2f11778d1390124a855a6f289eb03659bedb6552
3
+ size 2820313
SoccerTwos/SoccerTwos-8999972.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54045cc0b60f68695fd39b320e84930a42d3b4213ebddd6cde09601d194501b9
3
+ size 34740902
SoccerTwos/SoccerTwos-9499852.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501c0a13f8bfc69788fb5790ba8863229484b83dd2e9deecf27e7d2504aa576e
3
+ size 2820313
SoccerTwos/SoccerTwos-9499852.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299bf20e15715465cdf8c1396aa562d09385b26c4840db165eaf8d9a89272ea3
3
+ size 34740902
SoccerTwos/SoccerTwos-9999968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc800628b9ae195e43366fa3afb04a58a0c394396804b04af4b88696c863b58b
3
+ size 2820313
SoccerTwos/SoccerTwos-9999968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214625f2828e61170bed9de66969c1b2e92a0bf4bdd128c4d3618b9cf2f6cf52
3
+ size 34740902
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2955e17d961a2fdcd921d5a8a1aaba048e48b5faef6bed3a41f08d82c098689a
3
- size 28431030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87dc29b41d30b02d3c4442590d55e1ac4c416be51084e4b85fe284cb70c1e64b
3
+ size 34739782
SoccerTwos/events.out.tfevents.1700226013.dl-workstation.3599749.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3191d36bd2970cad990775e3fb9bcbda73e29192ce92f18524281552e5dde521
3
+ size 9768878
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": "./training-envs-executables/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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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": 0.97, "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": 3, "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": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 20, "play_against_latest_model_ratio": 0.5, "initial_elo": 1000.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-v1", "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
@@ -8,7 +8,7 @@ behaviors:
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
@@ -17,7 +17,7 @@ behaviors:
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
@@ -37,7 +37,7 @@ behaviors:
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
@@ -45,9 +45,9 @@ behaviors:
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:
53
  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64
@@ -70,7 +70,7 @@ engine_settings:
70
  no_graphics: true
71
  environment_parameters: null
72
  checkpoint_settings:
73
- run_id: SoccerTwos
74
  initialize_from: null
75
  load_model: false
76
  resume: false
 
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
+ lambd: 0.97
12
  num_epoch: 3
13
  learning_rate_schedule: constant
14
  beta_schedule: constant
 
17
  network_settings:
18
  normalize: false
19
  hidden_units: 512
20
+ num_layers: 3
21
  vis_encode_type: simple
22
  memory: null
23
  goal_conditioning_type: hyper
 
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
+ max_steps: 10000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
45
  save_steps: 50000
46
  team_change: 200000
47
  swap_steps: 2000
48
+ window: 20
49
  play_against_latest_model_ratio: 0.5
50
+ initial_elo: 1000.0
51
  behavioral_cloning: null
52
  env_settings:
53
  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64
 
70
  no_graphics: true
71
  environment_parameters: null
72
  checkpoint_settings:
73
+ run_id: SoccerTwos-v1
74
  initialize_from: null
75
  load_model: false
76
  resume: false
run_logs/Player-0.log CHANGED
@@ -11,7 +11,7 @@ NullGfxDevice:
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
- - Completed reload, in 0.039 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
- UnloadTime: 0.405239 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
@@ -818,62 +818,12 @@ TOO LONG
818
  TOO LONG
819
  TOO LONG
820
  TOO LONG
821
- TOO LONG
822
- TOO LONG
823
- TOO LONG
824
- TOO LONG
825
- TOO LONG
826
- TOO LONG
827
- TOO LONG
828
- TOO LONG
829
- TOO LONG
830
- TOO LONG
831
- TOO LONG
832
- TOO LONG
833
- TOO LONG
834
- TOO LONG
835
- TOO LONG
836
- TOO LONG
837
- TOO LONG
838
- TOO LONG
839
- TOO LONG
840
- TOO LONG
841
- TOO LONG
842
- TOO LONG
843
- TOO LONG
844
- TOO LONG
845
- TOO LONG
846
- TOO LONG
847
- TOO LONG
848
- TOO LONG
849
- TOO LONG
850
- TOO LONG
851
- TOO LONG
852
- TOO LONG
853
- TOO LONG
854
- TOO LONG
855
- TOO LONG
856
- TOO LONG
857
- TOO LONG
858
- TOO LONG
859
- TOO LONG
860
- TOO LONG
861
- TOO LONG
862
- TOO LONG
863
- TOO LONG
864
- TOO LONG
865
- TOO LONG
866
- TOO LONG
867
- TOO LONG
868
- TOO LONG
869
- TOO LONG
870
- TOO LONG
871
  Setting up 16 worker threads for Enlighten.
872
  Memory Statistics:
873
  [ALLOC_TEMP_TLS] TLS Allocator
874
  StackAllocators :
875
  [ALLOC_TEMP_MAIN]
876
- Peak usage frame count: [8.0 KB-16.0 KB]: 95166 frames, [2.0 MB-4.0 MB]: 1 frames
877
  Initial Block Size 4.0 MB
878
  Current Block Size 4.0 MB
879
  Peak Allocated Bytes 2.1 MB
@@ -1013,12 +963,12 @@ Memory Statistics:
1013
  Current Block Size 256.0 KB
1014
  Peak Allocated Bytes 0 B
1015
  Overflow Count 0
1016
- [ALLOC_TEMP_Job.Worker 26]
1017
  Initial Block Size 256.0 KB
1018
  Current Block Size 256.0 KB
1019
  Peak Allocated Bytes 0 B
1020
  Overflow Count 0
1021
- [ALLOC_TEMP_Job.Worker 21]
1022
  Initial Block Size 256.0 KB
1023
  Current Block Size 256.0 KB
1024
  Peak Allocated Bytes 0 B
@@ -1028,7 +978,7 @@ Memory Statistics:
1028
  Current Block Size 256.0 KB
1029
  Peak Allocated Bytes 0 B
1030
  Overflow Count 0
1031
- [ALLOC_TEMP_Background Job.Worker 9]
1032
  Initial Block Size 32.0 KB
1033
  Current Block Size 32.0 KB
1034
  Peak Allocated Bytes 0 B
@@ -1038,7 +988,7 @@ Memory Statistics:
1038
  Current Block Size 256.0 KB
1039
  Peak Allocated Bytes 0 B
1040
  Overflow Count 0
1041
- [ALLOC_TEMP_Background Job.Worker 14]
1042
  Initial Block Size 32.0 KB
1043
  Current Block Size 32.0 KB
1044
  Peak Allocated Bytes 0 B
@@ -1091,7 +1041,7 @@ Memory Statistics:
1091
  [ALLOC_TEMP_Job.Worker 8]
1092
  Initial Block Size 256.0 KB
1093
  Current Block Size 256.0 KB
1094
- Peak Allocated Bytes 0 B
1095
  Overflow Count 0
1096
  [ALLOC_TEMP_Job.Worker 7]
1097
  Initial Block Size 256.0 KB
@@ -1106,7 +1056,7 @@ Memory Statistics:
1106
  [ALLOC_TEMP_Job.Worker 1]
1107
  Initial Block Size 256.0 KB
1108
  Current Block Size 256.0 KB
1109
- Peak Allocated Bytes 0.7 KB
1110
  Overflow Count 0
1111
  [ALLOC_TEMP_Job.Worker 10]
1112
  Initial Block Size 256.0 KB
@@ -1123,12 +1073,12 @@ Memory Statistics:
1123
  Current Block Size 256.0 KB
1124
  Peak Allocated Bytes 0 B
1125
  Overflow Count 0
1126
- [ALLOC_TEMP_Job.Worker 19]
1127
  Initial Block Size 256.0 KB
1128
  Current Block Size 256.0 KB
1129
  Peak Allocated Bytes 0 B
1130
  Overflow Count 0
1131
- [ALLOC_TEMP_Job.Worker 12]
1132
  Initial Block Size 256.0 KB
1133
  Current Block Size 256.0 KB
1134
  Peak Allocated Bytes 0 B
@@ -1145,16 +1095,16 @@ Memory Statistics:
1145
  Used Block count 1
1146
  Peak Allocated bytes 1.0 MB
1147
  [ALLOC_DEFAULT_MAIN]
1148
- Peak usage frame count: [4.0 MB-8.0 MB]: 95167 frames
1149
  Requested Block Size 16.0 MB
1150
  Peak Block count 1
1151
- Peak Allocated memory 4.9 MB
1152
  Peak Large allocation bytes 0 B
1153
  [ALLOC_DEFAULT_THREAD]
1154
- Peak usage frame count: [16.0 MB-32.0 MB]: 95167 frames
1155
  Requested Block Size 16.0 MB
1156
  Peak Block count 1
1157
- Peak Allocated memory 17.4 MB
1158
  Peak Large allocation bytes 16.0 MB
1159
  [ALLOC_TEMP_JOB_1_FRAME]
1160
  Initial Block Size 2.0 MB
@@ -1183,13 +1133,13 @@ Memory Statistics:
1183
  Used Block count 1
1184
  Peak Allocated bytes 1.0 MB
1185
  [ALLOC_GFX_MAIN]
1186
- Peak usage frame count: [32.0 KB-64.0 KB]: 95166 frames, [64.0 KB-128.0 KB]: 1 frames
1187
  Requested Block Size 16.0 MB
1188
  Peak Block count 1
1189
  Peak Allocated memory 65.6 KB
1190
  Peak Large allocation bytes 0 B
1191
  [ALLOC_GFX_THREAD]
1192
- Peak usage frame count: [128.0 KB-256.0 KB]: 95167 frames
1193
  Requested Block Size 16.0 MB
1194
  Peak Block count 1
1195
  Peak Allocated memory 173.5 KB
@@ -1201,16 +1151,16 @@ Memory Statistics:
1201
  Used Block count 1
1202
  Peak Allocated bytes 1.0 MB
1203
  [ALLOC_CACHEOBJECTS_MAIN]
1204
- Peak usage frame count: [0.5 MB-1.0 MB]: 95167 frames
1205
  Requested Block Size 4.0 MB
1206
  Peak Block count 1
1207
  Peak Allocated memory 0.6 MB
1208
  Peak Large allocation bytes 0 B
1209
  [ALLOC_CACHEOBJECTS_THREAD]
1210
- Peak usage frame count: [0.5 MB-1.0 MB]: 95166 frames, [4.0 MB-8.0 MB]: 1 frames
1211
  Requested Block Size 4.0 MB
1212
  Peak Block count 2
1213
- Peak Allocated memory 4.5 MB
1214
  Peak Large allocation bytes 0 B
1215
  [ALLOC_TYPETREE] Dual Thread Allocator
1216
  Peak main deferred allocation count 0
@@ -1219,13 +1169,13 @@ Memory Statistics:
1219
  Used Block count 1
1220
  Peak Allocated bytes 1.0 MB
1221
  [ALLOC_TYPETREE_MAIN]
1222
- Peak usage frame count: [0-1.0 KB]: 95167 frames
1223
  Requested Block Size 2.0 MB
1224
  Peak Block count 1
1225
  Peak Allocated memory 1.0 KB
1226
  Peak Large allocation bytes 0 B
1227
  [ALLOC_TYPETREE_THREAD]
1228
- Peak usage frame count: [1.0 KB-2.0 KB]: 95166 frames, [2.0 KB-4.0 KB]: 1 frames
1229
  Requested Block Size 2.0 MB
1230
  Peak Block count 1
1231
  Peak Allocated memory 2.2 KB
 
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.045 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
+ UnloadTime: 0.750077 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
 
818
  TOO LONG
819
  TOO LONG
820
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
821
  Setting up 16 worker threads for Enlighten.
822
  Memory Statistics:
823
  [ALLOC_TEMP_TLS] TLS Allocator
824
  StackAllocators :
825
  [ALLOC_TEMP_MAIN]
826
+ Peak usage frame count: [8.0 KB-16.0 KB]: 189268 frames, [2.0 MB-4.0 MB]: 1 frames
827
  Initial Block Size 4.0 MB
828
  Current Block Size 4.0 MB
829
  Peak Allocated Bytes 2.1 MB
 
963
  Current Block Size 256.0 KB
964
  Peak Allocated Bytes 0 B
965
  Overflow Count 0
966
+ [ALLOC_TEMP_Job.Worker 21]
967
  Initial Block Size 256.0 KB
968
  Current Block Size 256.0 KB
969
  Peak Allocated Bytes 0 B
970
  Overflow Count 0
971
+ [ALLOC_TEMP_Job.Worker 26]
972
  Initial Block Size 256.0 KB
973
  Current Block Size 256.0 KB
974
  Peak Allocated Bytes 0 B
 
978
  Current Block Size 256.0 KB
979
  Peak Allocated Bytes 0 B
980
  Overflow Count 0
981
+ [ALLOC_TEMP_Background Job.Worker 14]
982
  Initial Block Size 32.0 KB
983
  Current Block Size 32.0 KB
984
  Peak Allocated Bytes 0 B
 
988
  Current Block Size 256.0 KB
989
  Peak Allocated Bytes 0 B
990
  Overflow Count 0
991
+ [ALLOC_TEMP_Background Job.Worker 9]
992
  Initial Block Size 32.0 KB
993
  Current Block Size 32.0 KB
994
  Peak Allocated Bytes 0 B
 
1041
  [ALLOC_TEMP_Job.Worker 8]
1042
  Initial Block Size 256.0 KB
1043
  Current Block Size 256.0 KB
1044
+ Peak Allocated Bytes 0.7 KB
1045
  Overflow Count 0
1046
  [ALLOC_TEMP_Job.Worker 7]
1047
  Initial Block Size 256.0 KB
 
1056
  [ALLOC_TEMP_Job.Worker 1]
1057
  Initial Block Size 256.0 KB
1058
  Current Block Size 256.0 KB
1059
+ Peak Allocated Bytes 0 B
1060
  Overflow Count 0
1061
  [ALLOC_TEMP_Job.Worker 10]
1062
  Initial Block Size 256.0 KB
 
1073
  Current Block Size 256.0 KB
1074
  Peak Allocated Bytes 0 B
1075
  Overflow Count 0
1076
+ [ALLOC_TEMP_Job.Worker 12]
1077
  Initial Block Size 256.0 KB
1078
  Current Block Size 256.0 KB
1079
  Peak Allocated Bytes 0 B
1080
  Overflow Count 0
1081
+ [ALLOC_TEMP_Job.Worker 19]
1082
  Initial Block Size 256.0 KB
1083
  Current Block Size 256.0 KB
1084
  Peak Allocated Bytes 0 B
 
1095
  Used Block count 1
1096
  Peak Allocated bytes 1.0 MB
1097
  [ALLOC_DEFAULT_MAIN]
1098
+ Peak usage frame count: [4.0 MB-8.0 MB]: 189269 frames
1099
  Requested Block Size 16.0 MB
1100
  Peak Block count 1
1101
+ Peak Allocated memory 5.0 MB
1102
  Peak Large allocation bytes 0 B
1103
  [ALLOC_DEFAULT_THREAD]
1104
+ Peak usage frame count: [16.0 MB-32.0 MB]: 189269 frames
1105
  Requested Block Size 16.0 MB
1106
  Peak Block count 1
1107
+ Peak Allocated memory 17.3 MB
1108
  Peak Large allocation bytes 16.0 MB
1109
  [ALLOC_TEMP_JOB_1_FRAME]
1110
  Initial Block Size 2.0 MB
 
1133
  Used Block count 1
1134
  Peak Allocated bytes 1.0 MB
1135
  [ALLOC_GFX_MAIN]
1136
+ Peak usage frame count: [32.0 KB-64.0 KB]: 189268 frames, [64.0 KB-128.0 KB]: 1 frames
1137
  Requested Block Size 16.0 MB
1138
  Peak Block count 1
1139
  Peak Allocated memory 65.6 KB
1140
  Peak Large allocation bytes 0 B
1141
  [ALLOC_GFX_THREAD]
1142
+ Peak usage frame count: [128.0 KB-256.0 KB]: 189269 frames
1143
  Requested Block Size 16.0 MB
1144
  Peak Block count 1
1145
  Peak Allocated memory 173.5 KB
 
1151
  Used Block count 1
1152
  Peak Allocated bytes 1.0 MB
1153
  [ALLOC_CACHEOBJECTS_MAIN]
1154
+ Peak usage frame count: [0.5 MB-1.0 MB]: 189269 frames
1155
  Requested Block Size 4.0 MB
1156
  Peak Block count 1
1157
  Peak Allocated memory 0.6 MB
1158
  Peak Large allocation bytes 0 B
1159
  [ALLOC_CACHEOBJECTS_THREAD]
1160
+ Peak usage frame count: [0.5 MB-1.0 MB]: 189268 frames, [4.0 MB-8.0 MB]: 1 frames
1161
  Requested Block Size 4.0 MB
1162
  Peak Block count 2
1163
+ Peak Allocated memory 4.4 MB
1164
  Peak Large allocation bytes 0 B
1165
  [ALLOC_TYPETREE] Dual Thread Allocator
1166
  Peak main deferred allocation count 0
 
1169
  Used Block count 1
1170
  Peak Allocated bytes 1.0 MB
1171
  [ALLOC_TYPETREE_MAIN]
1172
+ Peak usage frame count: [0-1.0 KB]: 189269 frames
1173
  Requested Block Size 2.0 MB
1174
  Peak Block count 1
1175
  Peak Allocated memory 1.0 KB
1176
  Peak Large allocation bytes 0 B
1177
  [ALLOC_TYPETREE_THREAD]
1178
+ Peak usage frame count: [1.0 KB-2.0 KB]: 189268 frames, [2.0 KB-4.0 KB]: 1 frames
1179
  Requested Block Size 2.0 MB
1180
  Peak Block count 1
1181
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,261 +2,261 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 1.9461054801940918,
6
- "min": 1.904166579246521,
7
- "max": 3.2956230640411377,
8
- "count": 500
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 37053.84765625,
12
- "min": 17806.4453125,
13
- "max": 138916.96875,
14
- "count": 500
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 53.19565217391305,
18
- "min": 42.5,
19
  "max": 999.0,
20
- "count": 500
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 19576.0,
24
- "min": 15864.0,
25
- "max": 24968.0,
26
- "count": 500
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1561.4647984105638,
30
- "min": 1200.2176748263073,
31
- "max": 1569.6239443631198,
32
- "count": 449
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 287309.52290754375,
36
- "min": 2403.4385588692585,
37
- "max": 349943.248393054,
38
- "count": 449
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 4999934.0,
42
- "min": 9472.0,
43
- "max": 4999934.0,
44
- "count": 500
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 4999934.0,
48
- "min": 9472.0,
49
- "max": 4999934.0,
50
- "count": 500
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.0005880995886400342,
54
- "min": -0.10381485521793365,
55
- "max": 0.15578675270080566,
56
- "count": 500
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 0.10821032524108887,
60
- "min": -18.44150161743164,
61
- "max": 22.389698028564453,
62
- "count": 500
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": -0.003045535646378994,
66
- "min": -0.107919842004776,
67
- "max": 0.15591202676296234,
68
- "count": 500
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": -0.5603785514831543,
72
- "min": -19.42557144165039,
73
- "max": 22.077869415283203,
74
- "count": 500
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 500
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 500
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": -0.030989131849745045,
90
- "min": -0.6666666666666666,
91
- "max": 0.49531428870700656,
92
- "count": 500
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": -5.702000260353088,
96
- "min": -47.26379996538162,
97
- "max": 53.65780019760132,
98
- "count": 500
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": -0.030989131849745045,
102
- "min": -0.6666666666666666,
103
- "max": 0.49531428870700656,
104
- "count": 500
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": -5.702000260353088,
108
- "min": -47.26379996538162,
109
- "max": 53.65780019760132,
110
- "count": 500
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 500
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 500
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.01822344895529871,
126
- "min": 0.010149347697248838,
127
- "max": 0.02408516436504821,
128
- "count": 238
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.01822344895529871,
132
- "min": 0.010149347697248838,
133
- "max": 0.02408516436504821,
134
- "count": 238
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.11939934814969698,
138
- "min": 4.607257710631529e-06,
139
- "max": 0.12145202457904816,
140
- "count": 238
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.11939934814969698,
144
- "min": 4.607257710631529e-06,
145
- "max": 0.12145202457904816,
146
- "count": 238
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.12171256989240646,
150
- "min": 5.147514874200472e-06,
151
- "max": 0.12289389173189799,
152
- "count": 238
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.12171256989240646,
156
- "min": 5.147514874200472e-06,
157
- "max": 0.12289389173189799,
158
- "count": 238
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
  "value": 0.0003,
162
  "min": 0.0003,
163
  "max": 0.0003,
164
- "count": 238
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
  "value": 0.0003,
168
  "min": 0.0003,
169
  "max": 0.0003,
170
- "count": 238
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
- "count": 238
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
- "count": 238
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
- "count": 238
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
- "count": 238
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1700220398",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
- "command_line_arguments": "/home/slsuser/anaconda3/envs/deeprl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
203
  "mlagents_envs_version": "1.1.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.1.0+cu121",
206
  "numpy_version": "1.21.2",
207
- "end_time_seconds": "1700225625"
208
  },
209
- "total": 5226.763361598132,
210
  "count": 1,
211
- "self": 0.21760607208125293,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.011837688041850924,
215
  "count": 1,
216
- "self": 0.011837688041850924
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 5226.533917838009,
220
  "count": 1,
221
- "self": 3.1301581186708063,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 1.4476710641756654,
225
- "count": 25,
226
- "self": 1.4476710641756654
227
  },
228
  "TrainerController.advance": {
229
- "total": 5221.86530762515,
230
- "count": 337696,
231
- "self": 3.252506673336029,
232
  "children": {
233
  "env_step": {
234
- "total": 4041.7462704849895,
235
- "count": 337696,
236
- "self": 3047.424466134282,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 992.2204488117713,
240
- "count": 337696,
241
- "self": 26.193338143872097,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 966.0271106678993,
245
- "count": 634458,
246
- "self": 966.0271106678993
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 2.101355538936332,
252
- "count": 337696,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 5220.487570376135,
257
- "count": 337696,
258
  "is_parallel": true,
259
- "self": 2614.88240986201,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +265,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.003215156029909849,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.0007425814401358366,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.0024725745897740126,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.0024725745897740126
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.019665183033794165,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.00039805308915674686,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.00034203799441456795,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.00034203799441456795
292
  },
293
  "communicator.exchange": {
294
- "total": 0.01764333201572299,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.01764333201572299
298
  },
299
  "steps_from_proto": {
300
- "total": 0.0012817599344998598,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.00024879188276827335,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.0010329680517315865,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.0010329680517315865
310
  }
311
  }
312
  }
@@ -315,50 +315,50 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 2605.555737106828,
319
- "count": 337695,
320
  "is_parallel": true,
321
- "self": 131.39839028660208,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 91.3645375308115,
325
- "count": 337695,
326
  "is_parallel": true,
327
- "self": 91.3645375308115
328
  },
329
  "communicator.exchange": {
330
- "total": 1975.620677822968,
331
- "count": 337695,
332
  "is_parallel": true,
333
- "self": 1975.620677822968
334
  },
335
  "steps_from_proto": {
336
- "total": 407.17213146644644,
337
- "count": 675390,
338
  "is_parallel": true,
339
- "self": 73.37821407383308,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 333.79391739261337,
343
- "count": 2701560,
344
  "is_parallel": true,
345
- "self": 333.79391739261337
346
  }
347
  }
348
  }
349
  }
350
  },
351
  "steps_from_proto": {
352
- "total": 0.049423407297581434,
353
- "count": 48,
354
  "is_parallel": true,
355
- "self": 0.009315095841884613,
356
  "children": {
357
  "_process_rank_one_or_two_observation": {
358
- "total": 0.04010831145569682,
359
- "count": 192,
360
  "is_parallel": true,
361
- "self": 0.04010831145569682
362
  }
363
  }
364
  }
@@ -369,31 +369,31 @@
369
  }
370
  },
371
  "trainer_advance": {
372
- "total": 1176.8665304668248,
373
- "count": 337696,
374
- "self": 30.876237988006324,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 424.9034292884171,
378
- "count": 337696,
379
- "self": 423.9219439262524,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
- "total": 0.9814853621646762,
383
- "count": 10,
384
- "self": 0.9814853621646762
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
- "total": 721.0868631904013,
390
- "count": 239,
391
- "self": 472.8956399273593,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
- "total": 248.19122326304205,
395
- "count": 7170,
396
- "self": 248.19122326304205
397
  }
398
  }
399
  }
@@ -402,19 +402,19 @@
402
  }
403
  },
404
  "trainer_threads": {
405
- "total": 5.110632628202438e-07,
406
  "count": 1,
407
- "self": 5.110632628202438e-07
408
  },
409
  "TrainerController._save_models": {
410
- "total": 0.09078051894903183,
411
  "count": 1,
412
- "self": 0.0009770221076905727,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
- "total": 0.08980349684134126,
416
  "count": 1,
417
- "self": 0.08980349684134126
418
  }
419
  }
420
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.5594910383224487,
6
+ "min": 1.5007145404815674,
7
+ "max": 3.2958080768585205,
8
+ "count": 1000
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 30441.265625,
12
+ "min": 19399.912109375,
13
+ "max": 128602.0625,
14
+ "count": 1000
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 50.91489361702128,
18
+ "min": 39.16528925619835,
19
  "max": 999.0,
20
+ "count": 1000
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19144.0,
24
+ "min": 13976.0,
25
+ "max": 28560.0,
26
+ "count": 1000
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1543.3786780823398,
30
+ "min": 993.6767511934177,
31
+ "max": 1570.0615274071952,
32
+ "count": 976
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 290155.1914794799,
36
+ "min": 1991.059276822115,
37
+ "max": 377381.6375228315,
38
+ "count": 976
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 9999968.0,
42
+ "min": 9296.0,
43
+ "max": 9999968.0,
44
+ "count": 1000
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 9999968.0,
48
+ "min": 9296.0,
49
+ "max": 9999968.0,
50
+ "count": 1000
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.020725328475236893,
54
+ "min": -0.14163443446159363,
55
+ "max": 0.33447977900505066,
56
+ "count": 1000
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 3.9170870780944824,
60
+ "min": -25.069293975830078,
61
+ "max": 45.955780029296875,
62
+ "count": 1000
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.027763523161411285,
66
+ "min": -0.14759673178195953,
67
+ "max": 0.3326408863067627,
68
+ "count": 1000
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 5.247305870056152,
72
+ "min": -26.124622344970703,
73
+ "max": 47.12504959106445,
74
+ "count": 1000
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 1000
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 1000
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.04137354553061188,
90
+ "min": -0.5,
91
+ "max": 0.7079642289053134,
92
+ "count": 1000
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 7.8196001052856445,
96
+ "min": -68.77140003442764,
97
+ "max": 88.84599977731705,
98
+ "count": 1000
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.04137354553061188,
102
+ "min": -0.5,
103
+ "max": 0.7079642289053134,
104
+ "count": 1000
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 7.8196001052856445,
108
+ "min": -68.77140003442764,
109
+ "max": 88.84599977731705,
110
+ "count": 1000
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 1000
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 1000
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.015625101576248804,
126
+ "min": 0.010895159827972142,
127
+ "max": 0.027467859897296876,
128
+ "count": 482
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.015625101576248804,
132
+ "min": 0.010895159827972142,
133
+ "max": 0.027467859897296876,
134
+ "count": 482
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.1730583036939303,
138
+ "min": 4.477435936678376e-06,
139
+ "max": 0.17462901572386424,
140
+ "count": 482
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.1730583036939303,
144
+ "min": 4.477435936678376e-06,
145
+ "max": 0.17462901572386424,
146
+ "count": 482
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.17562171320120493,
150
+ "min": 4.54882605633126e-06,
151
+ "max": 0.17695415963729222,
152
+ "count": 482
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.17562171320120493,
156
+ "min": 4.54882605633126e-06,
157
+ "max": 0.17695415963729222,
158
+ "count": 482
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
  "value": 0.0003,
162
  "min": 0.0003,
163
  "max": 0.0003,
164
+ "count": 482
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
  "value": 0.0003,
168
  "min": 0.0003,
169
  "max": 0.0003,
170
+ "count": 482
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
+ "count": 482
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
+ "count": 482
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
+ "count": 482
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
+ "count": 482
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1700226012",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/home/slsuser/anaconda3/envs/deeprl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-v1 --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
203
  "mlagents_envs_version": "1.1.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.1.0+cu121",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1700236614"
208
  },
209
+ "total": 10601.792952243006,
210
  "count": 1,
211
+ "self": 0.2177073829807341,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.012064563110470772,
215
  "count": 1,
216
+ "self": 0.012064563110470772
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 10601.563180296915,
220
  "count": 1,
221
+ "self": 6.469035892281681,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 1.770947635639459,
225
+ "count": 50,
226
+ "self": 1.770947635639459
227
  },
228
  "TrainerController.advance": {
229
+ "total": 10593.220908808056,
230
+ "count": 686281,
231
+ "self": 6.679624347947538,
232
  "children": {
233
  "env_step": {
234
+ "total": 8094.933057425311,
235
+ "count": 686281,
236
+ "self": 6087.868127197726,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 2002.8992128658574,
240
+ "count": 686281,
241
+ "self": 52.26499908720143,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 1950.634213778656,
245
+ "count": 1261818,
246
+ "self": 1950.634213778656
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 4.165717361727729,
252
+ "count": 686281,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 10591.178878826788,
257
+ "count": 686281,
258
  "is_parallel": true,
259
+ "self": 5369.61120087374,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0016926480457186699,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.00038940715603530407,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0013032408896833658,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.0013032408896833658
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.025538987945765257,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0005901888944208622,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00033575715497136116,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.00033575715497136116
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.022857312811538577,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.022857312811538577
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0017557290848344564,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.00033177854493260384,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.0014239505399018526,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.0014239505399018526
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 5221.466110505164,
319
+ "count": 686280,
320
  "is_parallel": true,
321
+ "self": 263.89104490960017,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 178.98514333437197,
325
+ "count": 686280,
326
  "is_parallel": true,
327
+ "self": 178.98514333437197
328
  },
329
  "communicator.exchange": {
330
+ "total": 3965.48220455274,
331
+ "count": 686280,
332
  "is_parallel": true,
333
+ "self": 3965.48220455274
334
  },
335
  "steps_from_proto": {
336
+ "total": 813.1077177084517,
337
+ "count": 1372560,
338
  "is_parallel": true,
339
+ "self": 146.47998522780836,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 666.6277324806433,
343
+ "count": 5490240,
344
  "is_parallel": true,
345
+ "self": 666.6277324806433
346
  }
347
  }
348
  }
349
  }
350
  },
351
  "steps_from_proto": {
352
+ "total": 0.10156744788400829,
353
+ "count": 98,
354
  "is_parallel": true,
355
+ "self": 0.018083795672282577,
356
  "children": {
357
  "_process_rank_one_or_two_observation": {
358
+ "total": 0.08348365221172571,
359
+ "count": 392,
360
  "is_parallel": true,
361
+ "self": 0.08348365221172571
362
  }
363
  }
364
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 2491.608227034798,
373
+ "count": 686281,
374
+ "self": 58.458906654966995,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 986.5126064775977,
378
+ "count": 686281,
379
+ "self": 984.3079594504088,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
+ "total": 2.204647027188912,
383
+ "count": 20,
384
+ "self": 2.204647027188912
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
+ "total": 1446.6367139022332,
390
+ "count": 482,
391
+ "self": 942.7734987116419,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 503.8632151905913,
395
+ "count": 14460,
396
+ "self": 503.8632151905913
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 5.709007382392883e-07,
406
  "count": 1,
407
+ "self": 5.709007382392883e-07
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.10228739003650844,
411
  "count": 1,
412
+ "self": 0.0012010070495307446,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.1010863829869777,
416
  "count": 1,
417
+ "self": 0.1010863829869777
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 3499962,
6
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499962.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1700223998.8838491,
9
  "auxillary_file_paths": [
10
- "results/SoccerTwos/SoccerTwos/SoccerTwos-3499962.pt"
11
  ]
12
  },
13
  {
14
- "steps": 3999974,
15
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999974.onnx",
16
  "reward": 0.0,
17
- "creation_time": 1700224535.9813187,
18
  "auxillary_file_paths": [
19
- "results/SoccerTwos/SoccerTwos/SoccerTwos-3999974.pt"
20
  ]
21
  },
22
  {
23
- "steps": 4499980,
24
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499980.onnx",
25
  "reward": 0.0,
26
- "creation_time": 1700225079.5536804,
27
  "auxillary_file_paths": [
28
- "results/SoccerTwos/SoccerTwos/SoccerTwos-4499980.pt"
29
  ]
30
  },
31
  {
32
- "steps": 4999934,
33
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999934.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1700225621.691056,
36
  "auxillary_file_paths": [
37
- "results/SoccerTwos/SoccerTwos/SoccerTwos-4999934.pt"
38
  ]
39
  },
40
  {
41
- "steps": 5000138,
42
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000138.onnx",
43
  "reward": 0.0,
44
- "creation_time": 1700225624.9117367,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwos/SoccerTwos/SoccerTwos-5000138.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1563.0653083334323,
51
  "final_checkpoint": {
52
- "steps": 5000138,
53
- "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
- "creation_time": 1700225624.9117367,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwos/SoccerTwos/SoccerTwos-5000138.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 8499977,
6
+ "file_path": "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-8499977.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1700234984.6186419,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-8499977.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 8999972,
15
+ "file_path": "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-8999972.onnx",
16
  "reward": 0.0,
17
+ "creation_time": 1700235525.7978852,
18
  "auxillary_file_paths": [
19
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-8999972.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 9499852,
24
+ "file_path": "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-9499852.onnx",
25
  "reward": 0.0,
26
+ "creation_time": 1700236069.8616965,
27
  "auxillary_file_paths": [
28
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-9499852.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 9999968,
33
+ "file_path": "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-9999968.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1700236614.2573187,
36
  "auxillary_file_paths": [
37
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-9999968.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 10000052,
42
+ "file_path": "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-10000052.onnx",
43
  "reward": 0.0,
44
+ "creation_time": 1700236614.3698,
45
  "auxillary_file_paths": [
46
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-10000052.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1542.9288766439201,
51
  "final_checkpoint": {
52
+ "steps": 10000052,
53
+ "file_path": "results/SoccerTwos-v1/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1700236614.3698,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos-v1/SoccerTwos/SoccerTwos-10000052.pt"
58
  ]
59
  }
60
  },