Hugging Face's logo

ThomasSimonini
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files Metrics Community
ThomasSimonini HF staff commited on
Commit
c929223
•
1 Parent(s): ba73a6e

Huggy upload after long training (2M t)

Browse files
Files changed (18) hide show
  1. Huggy.onnx +3 -0
  2. Huggy/Huggy-1499331.onnx +3 -0
  3. Huggy/Huggy-1499331.pt +3 -0
  4. Huggy/Huggy-1999977.onnx +3 -0
  5. Huggy/Huggy-1999977.pt +3 -0
  6. Huggy/Huggy-2000001.onnx +3 -0
  7. Huggy/Huggy-2000001.pt +3 -0
  8. Huggy/Huggy-499849.onnx +3 -0
  9. Huggy/Huggy-499849.pt +3 -0
  10. Huggy/Huggy-999633.onnx +3 -0
  11. Huggy/Huggy-999633.pt +3 -0
  12. Huggy/checkpoint.pt +3 -0
  13. Huggy/events.out.tfevents.1650462032.Thomas.15236.0 +3 -0
  14. README.md +26 -0
  15. config.json +1 -0
  16. configuration.yaml +75 -0
  17. run_logs/timers.json +327 -0
  18. run_logs/training_status.json +65 -0
Huggy.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8788b9318ecb60dc198ec0bc9e91d2205ddaa1528b8efc117526caf4158a47d1
3
+ size 2270368
Huggy/Huggy-1499331.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba5ce53547455d479533cac0b962d68b5d09f4c7f7a565e9a5897baeb4a0ab2
3
+ size 2270368
Huggy/Huggy-1499331.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9638f9405ec61697c62f6f44f5ceb9f7f9e5a6f156acf342791f50e812c5edb
3
+ size 13505711
Huggy/Huggy-1999977.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9913abcb91c7cc1b054f27d309e5a92790ed83f177c81efe16515e1b4baf54e0
3
+ size 2270368
Huggy/Huggy-1999977.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed117541c2ea12d328c8bc4bffc2bc9c697383f38fdfee2ffd55e31728c3539
3
+ size 13505711
Huggy/Huggy-2000001.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8788b9318ecb60dc198ec0bc9e91d2205ddaa1528b8efc117526caf4158a47d1
3
+ size 2270368
Huggy/Huggy-2000001.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36efb96586119e2e97be2d63f806f65011a05d2b7a69ecb0e0c570e457a6fe19
3
+ size 13505711
Huggy/Huggy-499849.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d2352b0c62d6d904b9c1563c09d99f9d2a494920825ef6dd6634d647580694
3
+ size 2270368
Huggy/Huggy-499849.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6efbd2aa3e683524a081e918f61be68f600d63d08593a73d69499534b27e75
3
+ size 13505711
Huggy/Huggy-999633.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf9de25bf0073226860a23f41161bd04f605db2b303136e9723dda9bb61b5a3
3
+ size 2270368
Huggy/Huggy-999633.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe076a8ef786738f3c94384b353c4133057f1679838622e93e1dab49ee2847e1
3
+ size 13505711
Huggy/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36efb96586119e2e97be2d63f806f65011a05d2b7a69ecb0e0c570e457a6fe19
3
+ size 13505711
Huggy/events.out.tfevents.1650462032.Thomas.15236.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9888d67739d68496f8e7671a85bd2cbfb29d66fd2fb8e2679b5ad3df4669d0d1
3
+ size 626831
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - unity-ml-agents
5
+ - ml-agents
6
+ - deep-reinforcement-learning
7
+ - reinforcement-learning
8
+ - Huggy
9
+ library_name: ml-agents
10
+ ---
11
+
12
+ # **ppo** Agent playing **Huggy**
13
+ This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
14
+
15
+ ## Usage (with ML-Agents)
16
+ ### Resume the training
17
+ ```
18
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
19
+ ```
20
+ ### Watch your Agent
21
+ 1. Move your model file into the environment Project
22
+ 2. Open the Unity Editor, and select the scene.
23
+ 3. Select the prefab Agent object.
24
+ 4. Drag the <behavior_name>.onnx file from the Project window of the Editor to the Model placeholder in the Agent inspector window.
25
+ 5. Press the Play button at the top of the Editor.
26
+
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "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": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "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": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy_1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Huggy:
4
+ trainer_type: ppo
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: linear
14
+ beta_schedule: linear
15
+ epsilon_schedule: linear
16
+ network_settings:
17
+ normalize: true
18
+ hidden_units: 512
19
+ num_layers: 3
20
+ vis_encode_type: simple
21
+ memory: null
22
+ goal_conditioning_type: hyper
23
+ deterministic: false
24
+ reward_signals:
25
+ extrinsic:
26
+ gamma: 0.995
27
+ strength: 1.0
28
+ network_settings:
29
+ normalize: false
30
+ hidden_units: 128
31
+ num_layers: 2
32
+ vis_encode_type: simple
33
+ memory: null
34
+ goal_conditioning_type: hyper
35
+ deterministic: false
36
+ init_path: null
37
+ keep_checkpoints: 5
38
+ checkpoint_interval: 500000
39
+ max_steps: 2000000
40
+ time_horizon: 1000
41
+ summary_freq: 30000
42
+ threaded: false
43
+ self_play: null
44
+ behavioral_cloning: null
45
+ env_settings:
46
+ env_path: null
47
+ env_args: null
48
+ base_port: 5005
49
+ num_envs: 1
50
+ num_areas: 1
51
+ seed: -1
52
+ max_lifetime_restarts: 10
53
+ restarts_rate_limit_n: 1
54
+ restarts_rate_limit_period_s: 60
55
+ engine_settings:
56
+ width: 84
57
+ height: 84
58
+ quality_level: 5
59
+ time_scale: 20
60
+ target_frame_rate: -1
61
+ capture_frame_rate: 60
62
+ no_graphics: false
63
+ environment_parameters: null
64
+ checkpoint_settings:
65
+ run_id: Huggy_1
66
+ initialize_from: null
67
+ load_model: false
68
+ resume: false
69
+ force: false
70
+ train_model: false
71
+ inference: false
72
+ results_dir: results
73
+ torch_settings:
74
+ device: null
75
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4065978527069092,
6
+ "min": 1.4065978527069092,
7
+ "max": 1.426931619644165,
8
+ "count": 66
9
+ },
10
+ "Huggy.Policy.Entropy.sum": {
11
+ "value": 42889.98046875,
12
+ "min": 40708.66796875,
13
+ "max": 46342.19921875,
14
+ "count": 66
15
+ },
16
+ "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 85.47727272727273,
18
+ "min": 83.74011299435028,
19
+ "max": 401.7866666666667,
20
+ "count": 66
21
+ },
22
+ "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 30088.0,
24
+ "min": 28987.0,
25
+ "max": 30422.0,
26
+ "count": 66
27
+ },
28
+ "Huggy.Step.mean": {
29
+ "value": 1979709.0,
30
+ "min": 29962.0,
31
+ "max": 1979709.0,
32
+ "count": 66
33
+ },
34
+ "Huggy.Step.sum": {
35
+ "value": 1979709.0,
36
+ "min": 29962.0,
37
+ "max": 1979709.0,
38
+ "count": 66
39
+ },
40
+ "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.4500532150268555,
42
+ "min": 0.16551850736141205,
43
+ "max": 2.4757072925567627,
44
+ "count": 66
45
+ },
46
+ "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 862.4187622070312,
48
+ "min": 12.248369216918945,
49
+ "max": 867.419677734375,
50
+ "count": 66
51
+ },
52
+ "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.806248088959943,
54
+ "min": 1.799411579966545,
55
+ "max": 3.883133729931655,
56
+ "count": 66
57
+ },
58
+ "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 1339.7993273139,
60
+ "min": 133.15645691752434,
61
+ "max": 1339.7993273139,
62
+ "count": 66
63
+ },
64
+ "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.806248088959943,
66
+ "min": 1.799411579966545,
67
+ "max": 3.883133729931655,
68
+ "count": 66
69
+ },
70
+ "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 1339.7993273139,
72
+ "min": 133.15645691752434,
73
+ "max": 1339.7993273139,
74
+ "count": 66
75
+ },
76
+ "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.017106848221616625,
78
+ "min": 0.011600281985010952,
79
+ "max": 0.022020238154800607,
80
+ "count": 66
81
+ },
82
+ "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.03421369644323325,
84
+ "min": 0.011600281985010952,
85
+ "max": 0.04135468834429048,
86
+ "count": 66
87
+ },
88
+ "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.05233929064124823,
90
+ "min": 0.020054462427894274,
91
+ "max": 0.06298484069605668,
92
+ "count": 66
93
+ },
94
+ "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.10467858128249646,
96
+ "min": 0.020054462427894274,
97
+ "max": 0.12434903296331565,
98
+ "count": 66
99
+ },
100
+ "Huggy.Policy.LearningRate.mean": {
101
+ "value": 4.942298352600014e-06,
102
+ "min": 4.942298352600014e-06,
103
+ "max": 0.0002968639510453499,
104
+ "count": 66
105
+ },
106
+ "Huggy.Policy.LearningRate.sum": {
107
+ "value": 9.884596705200027e-06,
108
+ "min": 9.566196811299996e-06,
109
+ "max": 0.00057822735725755,
110
+ "count": 66
111
+ },
112
+ "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.10164740000000003,
114
+ "min": 0.10164740000000003,
115
+ "max": 0.19895465000000004,
116
+ "count": 66
117
+ },
118
+ "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.20329480000000005,
120
+ "min": 0.10318870000000001,
121
+ "max": 0.39274244999999997,
122
+ "count": 66
123
+ },
124
+ "Huggy.Policy.Beta.mean": {
125
+ "value": 9.220526000000022e-05,
126
+ "min": 9.220526000000022e-05,
127
+ "max": 0.004947837035000002,
128
+ "count": 66
129
+ },
130
+ "Huggy.Policy.Beta.sum": {
131
+ "value": 0.00018441052000000045,
132
+ "min": 0.00016911613,
133
+ "max": 0.009637848255,
134
+ "count": 66
135
+ },
136
+ "Huggy.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 66
141
+ },
142
+ "Huggy.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 66
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1650462023",
152
+ "python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]",
153
+ "command_line_arguments": "C:\\Users\\simon\\Anaconda3\\envs\\mlagents\\Scripts\\mlagents-learn configuration.yaml --run-id=Huggy_1",
154
+ "mlagents_version": "0.29.0.dev0",
155
+ "mlagents_envs_version": "0.29.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.7.1+cu110",
158
+ "numpy_version": "1.22.3",
159
+ "end_time_seconds": "1650464973"
160
+ },
161
+ "total": 2950.5478018000003,
162
+ "count": 1,
163
+ "self": 0.011704999999892607,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.14496459999999978,
167
+ "count": 1,
168
+ "self": 0.14496459999999978
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 2950.3911322000004,
172
+ "count": 1,
173
+ "self": 4.680211899995811,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 13.165518,
177
+ "count": 1,
178
+ "self": 13.165518
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 2932.4152388000048,
182
+ "count": 231716,
183
+ "self": 4.528217499994753,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 2233.770497500003,
187
+ "count": 231716,
188
+ "self": 1508.5710400000391,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 721.7964393999812,
192
+ "count": 231716,
193
+ "self": 18.949565199852486,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 702.8468742001287,
197
+ "count": 222448,
198
+ "self": 469.1598053001096,
199
+ "children": {
200
+ "TorchPolicy.sample_actions": {
201
+ "total": 233.68706890001906,
202
+ "count": 222448,
203
+ "self": 233.68706890001906
204
+ }
205
+ }
206
+ }
207
+ }
208
+ },
209
+ "workers": {
210
+ "total": 3.403018099982507,
211
+ "count": 231716,
212
+ "self": 0.0,
213
+ "children": {
214
+ "worker_root": {
215
+ "total": 2933.761283299966,
216
+ "count": 231716,
217
+ "is_parallel": true,
218
+ "self": 1736.3023930999905,
219
+ "children": {
220
+ "steps_from_proto": {
221
+ "total": 0.002112600000000242,
222
+ "count": 1,
223
+ "is_parallel": true,
224
+ "self": 0.00023480000000120071,
225
+ "children": {
226
+ "_process_rank_one_or_two_observation": {
227
+ "total": 0.0018777999999990413,
228
+ "count": 2,
229
+ "is_parallel": true,
230
+ "self": 0.0018777999999990413
231
+ }
232
+ }
233
+ },
234
+ "UnityEnvironment.step": {
235
+ "total": 1197.4567775999758,
236
+ "count": 231716,
237
+ "is_parallel": true,
238
+ "self": 29.570126500104152,
239
+ "children": {
240
+ "UnityEnvironment._generate_step_input": {
241
+ "total": 83.97191599995509,
242
+ "count": 231716,
243
+ "is_parallel": true,
244
+ "self": 83.97191599995509
245
+ },
246
+ "communicator.exchange": {
247
+ "total": 1015.2412128999453,
248
+ "count": 231716,
249
+ "is_parallel": true,
250
+ "self": 1015.2412128999453
251
+ },
252
+ "steps_from_proto": {
253
+ "total": 68.67352219997139,
254
+ "count": 231716,
255
+ "is_parallel": true,
256
+ "self": 24.178702500072326,
257
+ "children": {
258
+ "_process_rank_one_or_two_observation": {
259
+ "total": 44.49481969989906,
260
+ "count": 463432,
261
+ "is_parallel": true,
262
+ "self": 44.49481969989906
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ }
269
+ }
270
+ }
271
+ }
272
+ }
273
+ },
274
+ "trainer_advance": {
275
+ "total": 694.1165238000074,
276
+ "count": 231716,
277
+ "self": 6.849092999982986,
278
+ "children": {
279
+ "process_trajectory": {
280
+ "total": 217.24021400002636,
281
+ "count": 231716,
282
+ "self": 216.58489650002633,
283
+ "children": {
284
+ "RLTrainer._checkpoint": {
285
+ "total": 0.6553175000000238,
286
+ "count": 4,
287
+ "self": 0.6553175000000238
288
+ }
289
+ }
290
+ },
291
+ "_update_policy": {
292
+ "total": 470.0272167999981,
293
+ "count": 97,
294
+ "self": 339.78801330000215,
295
+ "children": {
296
+ "TorchPPOOptimizer.update": {
297
+ "total": 130.23920349999594,
298
+ "count": 2910,
299
+ "self": 130.23920349999594
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ },
307
+ "trainer_threads": {
308
+ "total": 6.999998731771484e-07,
309
+ "count": 1,
310
+ "self": 6.999998731771484e-07
311
+ },
312
+ "TrainerController._save_models": {
313
+ "total": 0.13016280000010738,
314
+ "count": 1,
315
+ "self": 0.0036804000001211534,
316
+ "children": {
317
+ "RLTrainer._checkpoint": {
318
+ "total": 0.12648239999998623,
319
+ "count": 1,
320
+ "self": 0.12648239999998623
321
+ }
322
+ }
323
+ }
324
+ }
325
+ }
326
+ }
327
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Huggy": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 499849,
6
+ "file_path": "results\\Huggy_1\\Huggy\\Huggy-499849.onnx",
7
+ "reward": 3.8409776226166756,
8
+ "creation_time": 1650462766.9563007,
9
+ "auxillary_file_paths": [
10
+ "results\\Huggy_1\\Huggy\\Huggy-499849.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 999633,
15
+ "file_path": "results\\Huggy_1\\Huggy\\Huggy-999633.onnx",
16
+ "reward": 3.8536432950924606,
17
+ "creation_time": 1650463501.1990354,
18
+ "auxillary_file_paths": [
19
+ "results\\Huggy_1\\Huggy\\Huggy-999633.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 1499331,
24
+ "file_path": "results\\Huggy_1\\Huggy\\Huggy-1499331.onnx",
25
+ "reward": 3.8168014070605705,
26
+ "creation_time": 1650464251.328924,
27
+ "auxillary_file_paths": [
28
+ "results\\Huggy_1\\Huggy\\Huggy-1499331.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 1999977,
33
+ "file_path": "results\\Huggy_1\\Huggy\\Huggy-1999977.onnx",
34
+ "reward": 3.819167050448331,
35
+ "creation_time": 1650464973.5974445,
36
+ "auxillary_file_paths": [
37
+ "results\\Huggy_1\\Huggy\\Huggy-1999977.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 2000001,
42
+ "file_path": "results\\Huggy_1\\Huggy\\Huggy-2000001.onnx",
43
+ "reward": 3.7095100827839063,
44
+ "creation_time": 1650464973.7289164,
45
+ "auxillary_file_paths": [
46
+ "results\\Huggy_1\\Huggy\\Huggy-2000001.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 2000001,
52
+ "file_path": "results\\Huggy_1\\Huggy.onnx",
53
+ "reward": 3.7095100827839063,
54
+ "creation_time": 1650464973.7289164,
55
+ "auxillary_file_paths": [
56
+ "results\\Huggy_1\\Huggy\\Huggy-2000001.pt"
57
+ ]
58
+ }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "0.29.0.dev0",
63
+ "torch_version": "1.7.1+cu110"
64
+ }
65
+ }