Hugging Face's logo

ahforoughi
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
ahforoughi commited on
Commit
35f5911
•
1 Parent(s): 7d013c8

First Push

Browse files
Files changed (21) hide show
  1. README.md +35 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-19499978.onnx +3 -0
  4. SoccerTwos/SoccerTwos-19499978.pt +3 -0
  5. SoccerTwos/SoccerTwos-19999896.onnx +3 -0
  6. SoccerTwos/SoccerTwos-19999896.pt +3 -0
  7. SoccerTwos/SoccerTwos-20499992.onnx +3 -0
  8. SoccerTwos/SoccerTwos-20499992.pt +3 -0
  9. SoccerTwos/SoccerTwos-20999907.onnx +3 -0
  10. SoccerTwos/SoccerTwos-20999907.pt +3 -0
  11. SoccerTwos/SoccerTwos-21209724.onnx +3 -0
  12. SoccerTwos/SoccerTwos-21209724.pt +3 -0
  13. SoccerTwos/checkpoint.pt +3 -0
  14. SoccerTwos/events.out.tfevents.1714083662.Amirhossein.14779.0 +3 -0
  15. SoccerTwos/events.out.tfevents.1714083669.Amirhossein.15025.0 +3 -0
  16. SoccerTwos/events.out.tfevents.1714101220.Amirhossein.67206.0 +3 -0
  17. config.json +1 -0
  18. configuration.yaml +84 -0
  19. run_logs/Player-0.log +333 -0
  20. run_logs/timers.json +424 -0
  21. run_logs/training_status.json +66 -0
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - SoccerTwos
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-SoccerTwos
8
+ ---
9
+
10
+ # **poca** Agent playing **SoccerTwos**
11
+ This is a trained model of a **poca** agent playing **SoccerTwos**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: ahforoughi/poca-SoccerTwos
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aa6d7548a0aa94c97c658a1b4928bcb9805a120dce2a930a9a035fc3558706
3
+ size 2820313
SoccerTwos/SoccerTwos-19499978.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8dee75c728a5a7bbad82904f61c338b7c8727768932c715d6219cee129dbe43
3
+ size 2820313
SoccerTwos/SoccerTwos-19499978.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dcd48804bb69fe85bd03124b926a3a34693b200c48d984e2527d828d2892ce6
3
+ size 34741042
SoccerTwos/SoccerTwos-19999896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e968482a79f1ec993456da1697fe3703be523ad63598bde32212c7182edf4fe
3
+ size 2820313
SoccerTwos/SoccerTwos-19999896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b539532715cfca7b3db4fe35488a86fea072d9858c4bad91c75718f8958ea5
3
+ size 34741042
SoccerTwos/SoccerTwos-20499992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5400778f2f2eb2b54515a8115c913c6f0dcb407a9c45ae4ca2fe5c8025e7b15
3
+ size 2820313
SoccerTwos/SoccerTwos-20499992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67713eaab4657010f8c0de07e4c25f798e1013047f8d902ee505b5126e80586
3
+ size 34741042
SoccerTwos/SoccerTwos-20999907.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf172034f02f8352c93631d681c39ff6b92989f38cd375be808f7a33bbf61819
3
+ size 2820313
SoccerTwos/SoccerTwos-20999907.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f232711dfafaa83235e54ed4736bc44d5ee843a1912cfb1cc2830c55924cd26
3
+ size 34741042
SoccerTwos/SoccerTwos-21209724.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aa6d7548a0aa94c97c658a1b4928bcb9805a120dce2a930a9a035fc3558706
3
+ size 2820313
SoccerTwos/SoccerTwos-21209724.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f7f587a60b630b0dd2ab1074992dad0edb4ba227ded2e2cc3f03f9d55bdebe
3
+ size 34741042
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bc21e837ed1de0b6e68d23b2dfd6988e9e67289e61f9b651591c390642ef4d
3
+ size 34739782
SoccerTwos/events.out.tfevents.1714083662.Amirhossein.14779.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882af361255fb702616680be5f807fa0bb54f8281b372c0a5e035b9f7823e636
3
+ size 1241
SoccerTwos/events.out.tfevents.1714083669.Amirhossein.15025.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a8275cad4466825dd44d3ce442ac9ba20c1717442b36a60685113e22bc61e1
3
+ size 11251
SoccerTwos/events.out.tfevents.1714101220.Amirhossein.67206.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7980e0a855a02749d62705cf65be3dcf507b80fcfc3635e7c4241f2e6e6432
3
+ size 21644500
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.98, "num_epoch": 4, "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": 50000000, "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": "../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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SoccerTwos:
4
+ trainer_type: poca
5
+ hyperparameters:
6
+ batch_size: 1024
7
+ buffer_size: 20480
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.98
12
+ num_epoch: 4
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: 3
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.99
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ init_path: null
38
+ keep_checkpoints: 5
39
+ even_checkpoints: false
40
+ max_steps: 50000000
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:
53
+ env_path: ../SoccerTwos.x86_64
54
+ env_args: null
55
+ base_port: 5005
56
+ num_envs: 1
57
+ num_areas: 1
58
+ timeout_wait: 60
59
+ seed: -1
60
+ max_lifetime_restarts: 10
61
+ restarts_rate_limit_n: 1
62
+ restarts_rate_limit_period_s: 60
63
+ 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
71
+ no_graphics_monitor: false
72
+ environment_parameters: null
73
+ checkpoint_settings:
74
+ run_id: SoccerTwos
75
+ initialize_from: null
76
+ load_model: false
77
+ resume: true
78
+ force: false
79
+ train_model: false
80
+ inference: false
81
+ results_dir: results
82
+ torch_settings:
83
+ device: null
84
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/home/ubuntu20/projects/RL/huggy/SoccerTwos_Data/Managed'
2
+ Mono config path = '/home/ubuntu20/projects/RL/huggy/SoccerTwos_Data/MonoBleedingEdge/etc'
3
+ Preloaded 'lib_burst_generated.so'
4
+ Preloaded 'libgrpc_csharp_ext.x64.so'
5
+ Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
+ [Subsystems] Discovering subsystems at path /home/ubuntu20/projects/RL/huggy/SoccerTwos_Data/UnitySubsystems
7
+ Forcing GfxDevice: Null
8
+ GfxDevice: creating device client; threaded=0; jobified=0
9
+ NullGfxDevice:
10
+ Version: NULL 1.0 [1.0]
11
+ Renderer: Null Device
12
+ Vendor: Unity Technologies
13
+ Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.094 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)
18
+ WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
19
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
20
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
21
+ ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
22
+ WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
23
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
24
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
25
+ WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
26
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
27
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
28
+ ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
29
+ WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
30
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
31
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
32
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
33
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
34
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
35
+ ERROR: Shader Standard 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: 1.172500 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
43
+ TOO LONG
44
+ TOO LONG
45
+ TOO LONG
46
+ TOO LONG
47
+ TOO LONG
48
+ TOO LONG
49
+ TOO LONG
50
+ TOO LONG
51
+ TOO LONG
52
+ TOO LONG
53
+ TOO LONG
54
+ TOO LONG
55
+ TOO LONG
56
+ TOO LONG
57
+ TOO LONG
58
+ TOO LONG
59
+ TOO LONG
60
+ TOO LONG
61
+ TOO LONG
62
+ TOO LONG
63
+ TOO LONG
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
+ TOO LONG
130
+ TOO LONG
131
+ TOO LONG
132
+ TOO LONG
133
+ TOO LONG
134
+ TOO LONG
135
+ TOO LONG
136
+ TOO LONG
137
+ TOO LONG
138
+ TOO LONG
139
+ TOO LONG
140
+ TOO LONG
141
+ TOO LONG
142
+ TOO LONG
143
+ TOO LONG
144
+ TOO LONG
145
+ TOO LONG
146
+ TOO LONG
147
+ TOO LONG
148
+ TOO LONG
149
+ TOO LONG
150
+ TOO LONG
151
+ TOO LONG
152
+ TOO LONG
153
+ TOO LONG
154
+ TOO LONG
155
+ TOO LONG
156
+ TOO LONG
157
+ TOO LONG
158
+ TOO LONG
159
+ TOO LONG
160
+ TOO LONG
161
+ TOO LONG
162
+ TOO LONG
163
+ TOO LONG
164
+ TOO LONG
165
+ TOO LONG
166
+ TOO LONG
167
+ TOO LONG
168
+ TOO LONG
169
+ TOO LONG
170
+ TOO LONG
171
+ TOO LONG
172
+ TOO LONG
173
+ TOO LONG
174
+ TOO LONG
175
+ TOO LONG
176
+ TOO LONG
177
+ TOO LONG
178
+ TOO LONG
179
+ TOO LONG
180
+ TOO LONG
181
+ TOO LONG
182
+ TOO LONG
183
+ TOO LONG
184
+ TOO LONG
185
+ TOO LONG
186
+ TOO LONG
187
+ TOO LONG
188
+ TOO LONG
189
+ TOO LONG
190
+ TOO LONG
191
+ TOO LONG
192
+ TOO LONG
193
+ TOO LONG
194
+ TOO LONG
195
+ TOO LONG
196
+ TOO LONG
197
+ TOO LONG
198
+ TOO LONG
199
+ TOO LONG
200
+ TOO LONG
201
+ TOO LONG
202
+ TOO LONG
203
+ TOO LONG
204
+ TOO LONG
205
+ TOO LONG
206
+ TOO LONG
207
+ TOO LONG
208
+ TOO LONG
209
+ TOO LONG
210
+ TOO LONG
211
+ TOO LONG
212
+ TOO LONG
213
+ TOO LONG
214
+ TOO LONG
215
+ TOO LONG
216
+ TOO LONG
217
+ TOO LONG
218
+ TOO LONG
219
+ TOO LONG
220
+ TOO LONG
221
+ TOO LONG
222
+ TOO LONG
223
+ TOO LONG
224
+ TOO LONG
225
+ TOO LONG
226
+ TOO LONG
227
+ TOO LONG
228
+ TOO LONG
229
+ TOO LONG
230
+ TOO LONG
231
+ TOO LONG
232
+ TOO LONG
233
+ TOO LONG
234
+ TOO LONG
235
+ TOO LONG
236
+ TOO LONG
237
+ TOO LONG
238
+ TOO LONG
239
+ TOO LONG
240
+ TOO LONG
241
+ TOO LONG
242
+ TOO LONG
243
+ TOO LONG
244
+ TOO LONG
245
+ TOO LONG
246
+ TOO LONG
247
+ TOO LONG
248
+ TOO LONG
249
+ TOO LONG
250
+ TOO LONG
251
+ TOO LONG
252
+ TOO LONG
253
+ TOO LONG
254
+ TOO LONG
255
+ TOO LONG
256
+ TOO LONG
257
+ TOO LONG
258
+ TOO LONG
259
+ TOO LONG
260
+ TOO LONG
261
+ TOO LONG
262
+ TOO LONG
263
+ TOO LONG
264
+ TOO LONG
265
+ TOO LONG
266
+ TOO LONG
267
+ TOO LONG
268
+ TOO LONG
269
+ TOO LONG
270
+ TOO LONG
271
+ TOO LONG
272
+ TOO LONG
273
+ TOO LONG
274
+ TOO LONG
275
+ TOO LONG
276
+ TOO LONG
277
+ TOO LONG
278
+ TOO LONG
279
+ TOO LONG
280
+ TOO LONG
281
+ TOO LONG
282
+ TOO LONG
283
+ TOO LONG
284
+ TOO LONG
285
+ TOO LONG
286
+ TOO LONG
287
+ TOO LONG
288
+ TOO LONG
289
+ TOO LONG
290
+ TOO LONG
291
+ TOO LONG
292
+ TOO LONG
293
+ TOO LONG
294
+ TOO LONG
295
+ TOO LONG
296
+ TOO LONG
297
+ TOO LONG
298
+ TOO LONG
299
+ TOO LONG
300
+ TOO LONG
301
+ TOO LONG
302
+ TOO LONG
303
+ TOO LONG
304
+ TOO LONG
305
+ TOO LONG
306
+ TOO LONG
307
+ TOO LONG
308
+ TOO LONG
309
+ TOO LONG
310
+ TOO LONG
311
+ TOO LONG
312
+ TOO LONG
313
+ TOO LONG
314
+ TOO LONG
315
+ TOO LONG
316
+ TOO LONG
317
+ TOO LONG
318
+ TOO LONG
319
+ TOO LONG
320
+ TOO LONG
321
+ TOO LONG
322
+ TOO LONG
323
+ TOO LONG
324
+ TOO LONG
325
+ TOO LONG
326
+ TOO LONG
327
+ TOO LONG
328
+ TOO LONG
329
+ TOO LONG
330
+ TOO LONG
331
+ TOO LONG
332
+ TOO LONG
333
+ Setting up 12 worker threads for Enlighten.
run_logs/timers.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.7088449001312256,
6
+ "min": 1.6656020879745483,
7
+ "max": 3.295809745788574,
8
+ "count": 2118
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 30895.916015625,
12
+ "min": 17193.107421875,
13
+ "max": 105465.9140625,
14
+ "count": 2118
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 127.8974358974359,
18
+ "min": 53.077777777777776,
19
+ "max": 999.0,
20
+ "count": 2118
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19952.0,
24
+ "min": 9316.0,
25
+ "max": 31056.0,
26
+ "count": 2118
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1393.2070667626276,
30
+ "min": 1194.0179170001877,
31
+ "max": 1494.8070027585331,
32
+ "count": 2113
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 108670.15120748496,
36
+ "min": 2391.7424111429464,
37
+ "max": 268500.25612255756,
38
+ "count": 2113
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 21199822.0,
42
+ "min": 19812.0,
43
+ "max": 21199822.0,
44
+ "count": 2119
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 21199822.0,
48
+ "min": 19812.0,
49
+ "max": 21199822.0,
50
+ "count": 2119
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.11808216571807861,
54
+ "min": -0.15146400034427643,
55
+ "max": 0.13950079679489136,
56
+ "count": 2119
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -9.3284912109375,
60
+ "min": -21.204959869384766,
61
+ "max": 16.012798309326172,
62
+ "count": 2119
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.12490028887987137,
66
+ "min": -0.15625835955142975,
67
+ "max": 0.14536117017269135,
68
+ "count": 2119
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -9.867122650146484,
72
+ "min": -21.876171112060547,
73
+ "max": 16.468259811401367,
74
+ "count": 2119
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 2119
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 2119
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.16714936570276187,
90
+ "min": -0.6353999997178713,
91
+ "max": 0.4474086916964987,
92
+ "count": 2119
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -13.204799890518188,
96
+ "min": -59.412600100040436,
97
+ "max": 46.18160021305084,
98
+ "count": 2119
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.16714936570276187,
102
+ "min": -0.6353999997178713,
103
+ "max": 0.4474086916964987,
104
+ "count": 2119
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -13.204799890518188,
108
+ "min": -59.412600100040436,
109
+ "max": 46.18160021305084,
110
+ "count": 2119
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 2119
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 2119
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.041809182005818,
126
+ "min": 0.01977048081521172,
127
+ "max": 0.044036700596188895,
128
+ "count": 1024
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.041809182005818,
132
+ "min": 0.01977048081521172,
133
+ "max": 0.044036700596188895,
134
+ "count": 1024
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.07537970733828843,
138
+ "min": 0.0017333200696157292,
139
+ "max": 0.11558356927707791,
140
+ "count": 1024
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.07537970733828843,
144
+ "min": 0.0017333200696157292,
145
+ "max": 0.11558356927707791,
146
+ "count": 1024
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.08129970403388143,
150
+ "min": 0.0018409219002933242,
151
+ "max": 0.1513616295531392,
152
+ "count": 1024
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.08129970403388143,
156
+ "min": 0.0018409219002933242,
157
+ "max": 0.1513616295531392,
158
+ "count": 1024
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.00030000000000000003,
164
+ "count": 1024
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.00030000000000000003,
170
+ "count": 1024
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.19999999999999998,
174
+ "min": 0.19999999999999996,
175
+ "max": 0.19999999999999998,
176
+ "count": 1024
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.19999999999999998,
180
+ "min": 0.19999999999999996,
181
+ "max": 0.19999999999999998,
182
+ "count": 1024
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.004999999999999999,
186
+ "min": 0.004999999999999999,
187
+ "max": 0.005,
188
+ "count": 1024
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.004999999999999999,
192
+ "min": 0.004999999999999999,
193
+ "max": 0.005,
194
+ "count": 1024
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1714101219",
200
+ "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/home/ubuntu20/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
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": "2.3.0+cu121",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1714173699"
208
+ },
209
+ "total": 72479.418903871,
210
+ "count": 1,
211
+ "self": 10.004975321993697,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.00968369700058247,
215
+ "count": 1,
216
+ "self": 0.00968369700058247
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 72469.404244852,
220
+ "count": 1,
221
+ "self": 21.888783656962914,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 2.9812066590493487,
225
+ "count": 106,
226
+ "self": 2.9812066590493487
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 72444.219184276,
230
+ "count": 1429364,
231
+ "self": 23.230157327707275,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 58573.05581548553,
235
+ "count": 1429364,
236
+ "self": 18015.47316901359,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 40542.46051155147,
240
+ "count": 1429364,
241
+ "self": 183.41604163614102,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 40359.04446991533,
245
+ "count": 2665775,
246
+ "self": 40359.04446991533
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 15.122134920475219,
252
+ "count": 1429363,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 72423.0840364866,
257
+ "count": 1429363,
258
+ "is_parallel": true,
259
+ "self": 56851.92234566223,
260
+ "children": {
261
+ "run_training.setup": {
262
+ "total": 0.0,
263
+ "count": 0,
264
+ "is_parallel": true,
265
+ "self": 0.0,
266
+ "children": {
267
+ "steps_from_proto": {
268
+ "total": 0.0019098580014542677,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0005025739919801708,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0014072840094740968,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0014072840094740968
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.022356173998559825,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0003792550014622975,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0003022740020242054,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0003022740020242054
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.0205102519976208,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.0205102519976208
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0011643929974525236,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00025741099670995027,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0009069820007425733,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0009069820007425733
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 15571.059210241528,
319
+ "count": 1429362,
320
+ "is_parallel": true,
321
+ "self": 483.5320281779568,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 312.8383523944467,
325
+ "count": 1429362,
326
+ "is_parallel": true,
327
+ "self": 312.8383523944467
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 13387.107385548188,
331
+ "count": 1429362,
332
+ "is_parallel": true,
333
+ "self": 13387.107385548188
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 1387.5814441209368,
337
+ "count": 2858724,
338
+ "is_parallel": true,
339
+ "self": 290.3145172816985,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 1097.2669268392383,
343
+ "count": 11434896,
344
+ "is_parallel": true,
345
+ "self": 1097.2669268392383
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.102480582849239,
353
+ "count": 210,
354
+ "is_parallel": true,
355
+ "self": 0.021618372837110655,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.08086221001212834,
359
+ "count": 840,
360
+ "is_parallel": true,
361
+ "self": 0.08086221001212834
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 13847.933211462761,
373
+ "count": 1429363,
374
+ "self": 170.83017437849048,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 8711.664205260236,
378
+ "count": 1429363,
379
+ "self": 8698.837213972212,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 12.826991288024146,
383
+ "count": 42,
384
+ "self": 12.826991288024146
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 4965.438831824034,
390
+ "count": 1025,
391
+ "self": 1810.928020163461,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 3154.5108116605734,
395
+ "count": 82064,
396
+ "self": 3154.5108116605734
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 6.579939508810639e-07,
406
+ "count": 1,
407
+ "self": 6.579939508810639e-07
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.3150696020020405,
411
+ "count": 1,
412
+ "self": 0.021174097011680715,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.29389550499035977,
416
+ "count": 1,
417
+ "self": 0.29389550499035977
418
+ }
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "stats_format_version": "0.3.0",
4
+ "mlagents_version": "1.1.0.dev0",
5
+ "torch_version": "2.3.0+cu121"
6
+ },
7
+ "SoccerTwos": {
8
+ "elo": 1404.0025492145062,
9
+ "checkpoints": [
10
+ {
11
+ "steps": 19499978,
12
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19499978.onnx",
13
+ "reward": 0.0,
14
+ "creation_time": 1714168990.7650092,
15
+ "auxillary_file_paths": [
16
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-19499978.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 19999896,
21
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19999896.onnx",
22
+ "reward": 0.0,
23
+ "creation_time": 1714170160.6938703,
24
+ "auxillary_file_paths": [
25
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-19999896.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 20499992,
30
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-20499992.onnx",
31
+ "reward": 0.0,
32
+ "creation_time": 1714171454.6551592,
33
+ "auxillary_file_paths": [
34
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-20499992.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 20999907,
39
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-20999907.onnx",
40
+ "reward": 0.0,
41
+ "creation_time": 1714173171.2173288,
42
+ "auxillary_file_paths": [
43
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-20999907.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 21209724,
48
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-21209724.onnx",
49
+ "reward": 0.0,
50
+ "creation_time": 1714173689.0080009,
51
+ "auxillary_file_paths": [
52
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-21209724.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 21209724,
58
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
59
+ "reward": 0.0,
60
+ "creation_time": 1714173689.0080009,
61
+ "auxillary_file_paths": [
62
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-21209724.pt"
63
+ ]
64
+ }
65
+ }
66
+ }