Hugging Face's logo

Steddex
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files
xet
 Metrics Community
Steddex commited on
Commit
add84ec
·
1 Parent(s): 3f6a00e

First Push

Browse files
Files changed (17) hide show
  1. README.md +31 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-20382.onnx +3 -0
  4. SoccerTwos/SoccerTwos-20382.pt +3 -0
  5. SoccerTwos/SoccerTwos-499368.onnx +3 -0
  6. SoccerTwos/SoccerTwos-499368.pt +3 -0
  7. SoccerTwos/SoccerTwos-52604.onnx +3 -0
  8. SoccerTwos/SoccerTwos-52604.pt +3 -0
  9. SoccerTwos/checkpoint.pt +3 -0
  10. SoccerTwos/events.out.tfevents.1685022307.stephen-Vivobook.165085.0 +3 -0
  11. SoccerTwos/events.out.tfevents.1685022432.stephen-Vivobook.165482.0 +3 -0
  12. SoccerTwos/events.out.tfevents.1685022617.stephen-Vivobook.165848.0 +3 -0
  13. config.json +1 -0
  14. configuration.yaml +82 -0
  15. run_logs/Player-0.log +266 -0
  16. run_logs/timers.json +403 -0
  17. run_logs/training_status.json +39 -0
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - unity-ml-agents
5
+ - ml-agents
6
+ - deep-reinforcement-learning
7
+ - reinforcement-learning
8
+ - ML-Agents-SoccerTwos
9
+ library_name: ml-agents
10
+ ---
11
+
12
+ # **poca** Agent playing **SoccerTwos**
13
+ This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
14
+
15
+ ## Usage (with ML-Agents)
16
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+
19
+
20
+ ### Resume the training
21
+ ```
22
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
23
+ ```
24
+ ### Watch your Agent play
25
+ You can watch your agent **playing directly in your browser:**.
26
+
27
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
28
+ 2. Step 1: Write your model_id: Steddex/poca-SoccerTwos
29
+ 3. Step 2: Select your *.nn /*.onnx file
30
+ 4. Click on Watch the agent play 👀
31
+
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d504592fdd0049afb90615875d38856f596057fc848554da9853cd3a02f7ae2d
3
+ size 1764633
SoccerTwos/SoccerTwos-20382.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29dfe3a8fff5f1679bb099f18fdcfc6352c15b197fae9ee12e151f659038fabe
3
+ size 1764633
SoccerTwos/SoccerTwos-20382.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5c7ac461a1196a7947f4e046d1b9c68663420179729e2aeb54552064b01c2e
3
+ size 9478713
SoccerTwos/SoccerTwos-499368.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f40fd049657871c14a2ec25efeb250cbb859043bc781a6a0e90aad56b821ad4
3
+ size 1764633
SoccerTwos/SoccerTwos-499368.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dcd9d98203d899240b4bc69db1e37bc9f34fec3550bee2559e82c2a04ff257
3
+ size 28422481
SoccerTwos/SoccerTwos-52604.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d504592fdd0049afb90615875d38856f596057fc848554da9853cd3a02f7ae2d
3
+ size 1764633
SoccerTwos/SoccerTwos-52604.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9c0a120b4d4f50c7eca2decd17d564e786a5b6252bcd2b7585cc83b244fafb
3
+ size 28422417
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dcd9d98203d899240b4bc69db1e37bc9f34fec3550bee2559e82c2a04ff257
3
+ size 28422481
SoccerTwos/events.out.tfevents.1685022307.stephen-Vivobook.165085.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e4fed73337b73b514b3c3e5708919536d4c858923c7f6b5392a96bbf9626b2
3
+ size 21351
SoccerTwos/events.out.tfevents.1685022432.stephen-Vivobook.165482.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd3aabb9980b69c8e50a92acdccf757ee52825ee738023c768cc331848184de
3
+ size 27115
SoccerTwos/events.out.tfevents.1685022617.stephen-Vivobook.165848.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d60194726249dad1e05affa203ff28b2d2556c32208f2412a1f827b80260228
3
+ size 206244
config.json ADDED
@@ -0,0 +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": 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": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 1280, "height": 800, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": 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 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SoccerTwos:
4
+ trainer_type: poca
5
+ hyperparameters:
6
+ batch_size: 2048
7
+ buffer_size: 20480
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ learning_rate_schedule: constant
14
+ beta_schedule: constant
15
+ epsilon_schedule: constant
16
+ checkpoint_interval: 500000
17
+ network_settings:
18
+ normalize: false
19
+ hidden_units: 512
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.99
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
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: ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64
54
+ env_args: null
55
+ base_port: 5005
56
+ num_envs: 1
57
+ num_areas: 1
58
+ seed: -1
59
+ max_lifetime_restarts: 10
60
+ restarts_rate_limit_n: 1
61
+ restarts_rate_limit_period_s: 60
62
+ engine_settings:
63
+ width: 1280
64
+ height: 800
65
+ quality_level: 5
66
+ time_scale: 20
67
+ target_frame_rate: -1
68
+ capture_frame_rate: 60
69
+ no_graphics: false
70
+ environment_parameters: null
71
+ checkpoint_settings:
72
+ run_id: SoccerTwos
73
+ initialize_from: null
74
+ load_model: false
75
+ resume: true
76
+ force: false
77
+ train_model: false
78
+ inference: false
79
+ results_dir: results
80
+ torch_settings:
81
+ device: null
82
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/home/stephen/Personal/2023-05-24_DeepRL/deeprl_unit_7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
2
+ Mono config path = '/home/stephen/Personal/2023-05-24_DeepRL/deeprl_unit_7/ml-agents/training-envs-executables/SoccerTwos/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/stephen/Personal/2023-05-24_DeepRL/deeprl_unit_7/ml-agents/training-envs-executables/SoccerTwos/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 0.044 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: 0.522880 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 1280 x 800
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
run_logs/timers.json ADDED
@@ -0,0 +1,403 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.285490036010742,
6
+ "min": 3.285490036010742,
7
+ "max": 3.2957684993743896,
8
+ "count": 3
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 12300.875,
12
+ "min": 12300.875,
13
+ "max": 105464.59375,
14
+ "count": 3
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 999.0,
18
+ "min": 626.8,
19
+ "max": 999.0,
20
+ "count": 3
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19980.0,
24
+ "min": 12536.0,
25
+ "max": 29556.0,
26
+ "count": 3
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1200.6793840501775,
30
+ "min": 1200.6203859513396,
31
+ "max": 1200.6793840501775,
32
+ "count": 2
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 7204.076304301065,
36
+ "min": 7204.076304301065,
37
+ "max": 9604.963087610717,
38
+ "count": 2
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 49458.0,
42
+ "min": 29180.0,
43
+ "max": 49458.0,
44
+ "count": 3
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 49458.0,
48
+ "min": 29180.0,
49
+ "max": 49458.0,
50
+ "count": 3
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.03186836093664169,
54
+ "min": -0.04134928435087204,
55
+ "max": -0.03186836093664169,
56
+ "count": 3
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.3186836242675781,
60
+ "min": -0.5788899660110474,
61
+ "max": -0.3186836242675781,
62
+ "count": 3
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.026634126901626587,
66
+ "min": -0.041333843022584915,
67
+ "max": -0.026634126901626587,
68
+ "count": 3
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.26634126901626587,
72
+ "min": -0.578673779964447,
73
+ "max": -0.26634126901626587,
74
+ "count": 3
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 3
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 3
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.2,
90
+ "min": -0.2,
91
+ "max": 0.14334286536489213,
92
+ "count": 3
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -2.0,
96
+ "min": -2.0,
97
+ "max": 2.00680011510849,
98
+ "count": 3
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.2,
102
+ "min": -0.2,
103
+ "max": 0.14334286536489213,
104
+ "count": 3
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -2.0,
108
+ "min": -2.0,
109
+ "max": 2.00680011510849,
110
+ "count": 3
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 3
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 3
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.01693901012962063,
126
+ "min": 0.01693901012962063,
127
+ "max": 0.01693901012962063,
128
+ "count": 1
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01693901012962063,
132
+ "min": 0.01693901012962063,
133
+ "max": 0.01693901012962063,
134
+ "count": 1
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.00458185188472271,
138
+ "min": 0.00458185188472271,
139
+ "max": 0.00458185188472271,
140
+ "count": 1
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.00458185188472271,
144
+ "min": 0.00458185188472271,
145
+ "max": 0.00458185188472271,
146
+ "count": 1
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.004262195193829635,
150
+ "min": 0.004262195193829635,
151
+ "max": 0.004262195193829635,
152
+ "count": 1
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.004262195193829635,
156
+ "min": 0.004262195193829635,
157
+ "max": 0.004262195193829635,
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": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 1
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 1
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 1
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 1
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1685022429",
200
+ "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
201
+ "command_line_arguments": "/home/stephen/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume --width 1280 --height 800",
202
+ "mlagents_version": "0.31.0.dev0",
203
+ "mlagents_envs_version": "0.31.0.dev0",
204
+ "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "1.11.0+cu113",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1685022609"
208
+ },
209
+ "total": 180.58818536100443,
210
+ "count": 1,
211
+ "self": 0.058056558002135716,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.009422585004358552,
215
+ "count": 1,
216
+ "self": 0.009422585004358552
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 180.52070621799794,
220
+ "count": 1,
221
+ "self": 0.04852972851949744,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 5.816307453002082,
225
+ "count": 1,
226
+ "self": 5.816307453002082
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 174.49482808048197,
230
+ "count": 2413,
231
+ "self": 0.04377287132956553,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 168.1575938721071,
235
+ "count": 2413,
236
+ "self": 159.840035355679,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 8.287041545772809,
240
+ "count": 2413,
241
+ "self": 0.20523378730285913,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 8.08180775846995,
245
+ "count": 4804,
246
+ "self": 8.08180775846995
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 0.030516970655298792,
252
+ "count": 2412,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 180.23629833827727,
257
+ "count": 2412,
258
+ "is_parallel": true,
259
+ "self": 25.413429007967352,
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": 0.0020406220137374476,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.000417054005083628,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0016235680086538196,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0016235680086538196
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.10600702901137993,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.00014551301137544215,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.001452538010198623,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.001452538010198623
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.1026289250003174,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.1026289250003174
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0017800529894884676,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00026421698566991836,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0015158360038185492,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0015158360038185492
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 154.8228693303099,
319
+ "count": 2411,
320
+ "is_parallel": true,
321
+ "self": 0.3854865144530777,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 3.0791424944181927,
325
+ "count": 2411,
326
+ "is_parallel": true,
327
+ "self": 3.0791424944181927
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 147.00741965620546,
331
+ "count": 2411,
332
+ "is_parallel": true,
333
+ "self": 147.00741965620546
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 4.3508206652331864,
337
+ "count": 4822,
338
+ "is_parallel": true,
339
+ "self": 0.6526697288354626,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 3.698150936397724,
343
+ "count": 19288,
344
+ "is_parallel": true,
345
+ "self": 3.698150936397724
346
+ }
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ }
356
+ },
357
+ "trainer_advance": {
358
+ "total": 6.293461337045301,
359
+ "count": 2412,
360
+ "self": 0.25451349702780135,
361
+ "children": {
362
+ "process_trajectory": {
363
+ "total": 1.8358628840214806,
364
+ "count": 2412,
365
+ "self": 1.8358628840214806
366
+ },
367
+ "_update_policy": {
368
+ "total": 4.203084955996019,
369
+ "count": 1,
370
+ "self": 1.9739407319575548,
371
+ "children": {
372
+ "TorchPOCAOptimizer.update": {
373
+ "total": 2.229144224038464,
374
+ "count": 30,
375
+ "self": 2.229144224038464
376
+ }
377
+ }
378
+ }
379
+ }
380
+ }
381
+ }
382
+ },
383
+ "trainer_threads": {
384
+ "total": 8.409988367930055e-07,
385
+ "count": 1,
386
+ "self": 8.409988367930055e-07
387
+ },
388
+ "TrainerController._save_models": {
389
+ "total": 0.16104011499555781,
390
+ "count": 1,
391
+ "self": 0.0012124369968660176,
392
+ "children": {
393
+ "RLTrainer._checkpoint": {
394
+ "total": 0.1598276779986918,
395
+ "count": 1,
396
+ "self": 0.1598276779986918
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SoccerTwos": {
3
+ "elo": 1199.9263036958603,
4
+ "checkpoints": [
5
+ {
6
+ "steps": 20382,
7
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-20382.onnx",
8
+ "reward": 0.0,
9
+ "creation_time": 1685022415.7892632,
10
+ "auxillary_file_paths": [
11
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-20382.pt"
12
+ ]
13
+ },
14
+ {
15
+ "steps": 52604,
16
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-52604.onnx",
17
+ "reward": 0.0,
18
+ "creation_time": 1685022609.7467687,
19
+ "auxillary_file_paths": [
20
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-52604.pt"
21
+ ]
22
+ }
23
+ ],
24
+ "final_checkpoint": {
25
+ "steps": 52604,
26
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
27
+ "reward": 0.0,
28
+ "creation_time": 1685022609.7467687,
29
+ "auxillary_file_paths": [
30
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-52604.pt"
31
+ ]
32
+ }
33
+ },
34
+ "metadata": {
35
+ "stats_format_version": "0.3.0",
36
+ "mlagents_version": "0.31.0.dev0",
37
+ "torch_version": "1.11.0+cu113"
38
+ }
39
+ }