Hugging Face's logo

Rudolph314
/
ppo-PyramidsRND

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Model card Files Metrics Community
Rudolph314 commited on
Commit
eda0564
·
verified ·
1 Parent(s): 263cfa9

Pyramids first push

Browse files
Files changed (14) hide show
  1. Pyramids.onnx +3 -0
  2. Pyramids/Pyramids-1000084.onnx +3 -0
  3. Pyramids/Pyramids-1000084.pt +3 -0
  4. Pyramids/Pyramids-499943.onnx +3 -0
  5. Pyramids/Pyramids-499943.pt +3 -0
  6. Pyramids/Pyramids-999964.onnx +3 -0
  7. Pyramids/Pyramids-999964.pt +3 -0
  8. Pyramids/checkpoint.pt +3 -0
  9. Pyramids/events.out.tfevents.1713405784.DESKTOP-NDVELL8.20080.0 +3 -0
  10. README.md +35 -0
  11. config.json +1 -0
  12. configuration.yaml +91 -0
  13. run_logs/timers.json +356 -0
  14. run_logs/training_status.json +47 -0
Pyramids.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9b6a99c58e991a03855bb030cbbe32c9ffd4d35ab6c27df49c775a8f5afbca
3
+ size 1420238
Pyramids/Pyramids-1000084.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9b6a99c58e991a03855bb030cbbe32c9ffd4d35ab6c27df49c775a8f5afbca
3
+ size 1420238
Pyramids/Pyramids-1000084.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59cbab2cb5c47f7e6707b9c2b0a212d4d0ec336154f982509691b426f09424a9
3
+ size 8656252
Pyramids/Pyramids-499943.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f600af6e326445f4eed30aab2385456e1a2d9fc00e9fd888ea9c6da7484ddb91
3
+ size 1420238
Pyramids/Pyramids-499943.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf698b62240ca760809cc0fae77cfef745ebf3568da54ba544c20879f5daf0aa
3
+ size 8656173
Pyramids/Pyramids-999964.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9b6a99c58e991a03855bb030cbbe32c9ffd4d35ab6c27df49c775a8f5afbca
3
+ size 1420238
Pyramids/Pyramids-999964.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d7333240aedce563a9dc5905d378837a78e0175927c062d4dfa42e154c5ad1
3
+ size 8656173
Pyramids/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59b7a943418fa6fbc1c2b4322824c2911622a1bbaeb6a30fc79e317f3e44633
3
+ size 8655778
Pyramids/events.out.tfevents.1713405784.DESKTOP-NDVELL8.20080.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5988afc12ac448414a97040cd1a9d83ead15479964fef3d05d5dda5a94fff4
3
+ size 323534
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - Pyramids
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-Pyramids
8
+ ---
9
+
10
+ # **ppo** Agent playing **Pyramids**
11
+ This is a trained model of a **ppo** agent playing **Pyramids**
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: Rudolph314/ppo-PyramidsRND
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "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, "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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids1", "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 ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Pyramids:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 128
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
+ beta: 0.01
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ checkpoint_interval: 500000
18
+ network_settings:
19
+ normalize: false
20
+ hidden_units: 512
21
+ num_layers: 2
22
+ vis_encode_type: simple
23
+ memory: null
24
+ goal_conditioning_type: hyper
25
+ deterministic: false
26
+ reward_signals:
27
+ extrinsic:
28
+ gamma: 0.99
29
+ strength: 1.0
30
+ network_settings:
31
+ normalize: false
32
+ hidden_units: 128
33
+ num_layers: 2
34
+ vis_encode_type: simple
35
+ memory: null
36
+ goal_conditioning_type: hyper
37
+ deterministic: false
38
+ rnd:
39
+ gamma: 0.99
40
+ strength: 0.01
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 64
44
+ num_layers: 3
45
+ vis_encode_type: simple
46
+ memory: null
47
+ goal_conditioning_type: hyper
48
+ deterministic: false
49
+ learning_rate: 0.0001
50
+ encoding_size: null
51
+ init_path: null
52
+ keep_checkpoints: 5
53
+ even_checkpoints: false
54
+ max_steps: 1000000
55
+ time_horizon: 128
56
+ summary_freq: 30000
57
+ threaded: false
58
+ self_play: null
59
+ behavioral_cloning: null
60
+ env_settings:
61
+ env_path: null
62
+ env_args: null
63
+ base_port: 5005
64
+ num_envs: 1
65
+ num_areas: 1
66
+ timeout_wait: 60
67
+ seed: -1
68
+ max_lifetime_restarts: 10
69
+ restarts_rate_limit_n: 1
70
+ restarts_rate_limit_period_s: 60
71
+ engine_settings:
72
+ width: 84
73
+ height: 84
74
+ quality_level: 5
75
+ time_scale: 20
76
+ target_frame_rate: -1
77
+ capture_frame_rate: 60
78
+ no_graphics: false
79
+ environment_parameters: null
80
+ checkpoint_settings:
81
+ run_id: Pyramids1
82
+ initialize_from: null
83
+ load_model: false
84
+ resume: false
85
+ force: true
86
+ train_model: false
87
+ inference: false
88
+ results_dir: results
89
+ torch_settings:
90
+ device: null
91
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Pyramids.Policy.Entropy.mean": {
5
+ "value": 0.5022304058074951,
6
+ "min": 0.5022304058074951,
7
+ "max": 1.4404478073120117,
8
+ "count": 33
9
+ },
10
+ "Pyramids.Policy.Entropy.sum": {
11
+ "value": 15091.01953125,
12
+ "min": 15091.01953125,
13
+ "max": 43697.42578125,
14
+ "count": 33
15
+ },
16
+ "Pyramids.Step.mean": {
17
+ "value": 989928.0,
18
+ "min": 29952.0,
19
+ "max": 989928.0,
20
+ "count": 33
21
+ },
22
+ "Pyramids.Step.sum": {
23
+ "value": 989928.0,
24
+ "min": 29952.0,
25
+ "max": 989928.0,
26
+ "count": 33
27
+ },
28
+ "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.5391917824745178,
30
+ "min": -0.09371354430913925,
31
+ "max": 0.6504647731781006,
32
+ "count": 33
33
+ },
34
+ "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 149.8953094482422,
36
+ "min": -22.49125099182129,
37
+ "max": 186.03292846679688,
38
+ "count": 33
39
+ },
40
+ "Pyramids.Policy.RndValueEstimate.mean": {
41
+ "value": 0.23458337783813477,
42
+ "min": -0.009244040586054325,
43
+ "max": 0.4205356240272522,
44
+ "count": 33
45
+ },
46
+ "Pyramids.Policy.RndValueEstimate.sum": {
47
+ "value": 65.21417999267578,
48
+ "min": -2.3942065238952637,
49
+ "max": 101.34908294677734,
50
+ "count": 33
51
+ },
52
+ "Pyramids.Losses.PolicyLoss.mean": {
53
+ "value": 0.06721086604964166,
54
+ "min": 0.06721086604964166,
55
+ "max": 0.07436907960628135,
56
+ "count": 33
57
+ },
58
+ "Pyramids.Losses.PolicyLoss.sum": {
59
+ "value": 0.9409521246949832,
60
+ "min": 0.49425760968240384,
61
+ "max": 1.0606673738751424,
62
+ "count": 33
63
+ },
64
+ "Pyramids.Losses.ValueLoss.mean": {
65
+ "value": 0.023176299208509072,
66
+ "min": 0.00018794098207277637,
67
+ "max": 0.023176299208509072,
68
+ "count": 33
69
+ },
70
+ "Pyramids.Losses.ValueLoss.sum": {
71
+ "value": 0.324468188919127,
72
+ "min": 0.00206735080280054,
73
+ "max": 0.324468188919127,
74
+ "count": 33
75
+ },
76
+ "Pyramids.Policy.LearningRate.mean": {
77
+ "value": 7.59215461217143e-06,
78
+ "min": 7.59215461217143e-06,
79
+ "max": 0.00029515063018788575,
80
+ "count": 33
81
+ },
82
+ "Pyramids.Policy.LearningRate.sum": {
83
+ "value": 0.00010629016457040002,
84
+ "min": 0.00010629016457040002,
85
+ "max": 0.0035082908305698003,
86
+ "count": 33
87
+ },
88
+ "Pyramids.Policy.Epsilon.mean": {
89
+ "value": 0.10253068571428572,
90
+ "min": 0.10253068571428572,
91
+ "max": 0.19838354285714285,
92
+ "count": 33
93
+ },
94
+ "Pyramids.Policy.Epsilon.sum": {
95
+ "value": 1.4354296000000002,
96
+ "min": 1.3886848,
97
+ "max": 2.5694301999999998,
98
+ "count": 33
99
+ },
100
+ "Pyramids.Policy.Beta.mean": {
101
+ "value": 0.0002628155028571429,
102
+ "min": 0.0002628155028571429,
103
+ "max": 0.00983851593142857,
104
+ "count": 33
105
+ },
106
+ "Pyramids.Policy.Beta.sum": {
107
+ "value": 0.0036794170400000006,
108
+ "min": 0.0036794170400000006,
109
+ "max": 0.11696607698000001,
110
+ "count": 33
111
+ },
112
+ "Pyramids.Losses.RNDLoss.mean": {
113
+ "value": 0.014751069247722626,
114
+ "min": 0.014751069247722626,
115
+ "max": 0.5013335943222046,
116
+ "count": 33
117
+ },
118
+ "Pyramids.Losses.RNDLoss.sum": {
119
+ "value": 0.20651496946811676,
120
+ "min": 0.20651496946811676,
121
+ "max": 3.5093350410461426,
122
+ "count": 33
123
+ },
124
+ "Pyramids.Environment.EpisodeLength.mean": {
125
+ "value": 357.5,
126
+ "min": 306.1340206185567,
127
+ "max": 999.0,
128
+ "count": 33
129
+ },
130
+ "Pyramids.Environment.EpisodeLength.sum": {
131
+ "value": 30030.0,
132
+ "min": 15984.0,
133
+ "max": 33252.0,
134
+ "count": 33
135
+ },
136
+ "Pyramids.Environment.CumulativeReward.mean": {
137
+ "value": 1.5472404547035694,
138
+ "min": -1.0000000521540642,
139
+ "max": 1.6526205979057194,
140
+ "count": 33
141
+ },
142
+ "Pyramids.Environment.CumulativeReward.sum": {
143
+ "value": 129.96819819509983,
144
+ "min": -31.998001664876938,
145
+ "max": 162.45919826626778,
146
+ "count": 33
147
+ },
148
+ "Pyramids.Policy.ExtrinsicReward.mean": {
149
+ "value": 1.5472404547035694,
150
+ "min": -1.0000000521540642,
151
+ "max": 1.6526205979057194,
152
+ "count": 33
153
+ },
154
+ "Pyramids.Policy.ExtrinsicReward.sum": {
155
+ "value": 129.96819819509983,
156
+ "min": -31.998001664876938,
157
+ "max": 162.45919826626778,
158
+ "count": 33
159
+ },
160
+ "Pyramids.Policy.RndReward.mean": {
161
+ "value": 0.054536744301523346,
162
+ "min": 0.048960513193742373,
163
+ "max": 9.722250569611788,
164
+ "count": 33
165
+ },
166
+ "Pyramids.Policy.RndReward.sum": {
167
+ "value": 4.581086521327961,
168
+ "min": 4.581086521327961,
169
+ "max": 155.5560091137886,
170
+ "count": 33
171
+ },
172
+ "Pyramids.IsTraining.mean": {
173
+ "value": 1.0,
174
+ "min": 1.0,
175
+ "max": 1.0,
176
+ "count": 33
177
+ },
178
+ "Pyramids.IsTraining.sum": {
179
+ "value": 1.0,
180
+ "min": 1.0,
181
+ "max": 1.0,
182
+ "count": 33
183
+ }
184
+ },
185
+ "metadata": {
186
+ "timer_format_version": "0.1.0",
187
+ "start_time_seconds": "1713405599",
188
+ "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
189
+ "command_line_arguments": "\\\\?\\C:\\Users\\User\\miniconda3\\envs\\mlagents2\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --run-id=Pyramids1 --force",
190
+ "mlagents_version": "1.0.0",
191
+ "mlagents_envs_version": "1.0.0",
192
+ "communication_protocol_version": "1.5.0",
193
+ "pytorch_version": "2.2.2+cu121",
194
+ "numpy_version": "1.23.5",
195
+ "end_time_seconds": "1713407404"
196
+ },
197
+ "total": 1804.3917729000095,
198
+ "count": 1,
199
+ "self": 0.007547500004875474,
200
+ "children": {
201
+ "run_training.setup": {
202
+ "total": 0.08253529999637976,
203
+ "count": 1,
204
+ "self": 0.08253529999637976
205
+ },
206
+ "TrainerController.start_learning": {
207
+ "total": 1804.3016901000083,
208
+ "count": 1,
209
+ "self": 1.1507498003920773,
210
+ "children": {
211
+ "TrainerController._reset_env": {
212
+ "total": 188.4758612000005,
213
+ "count": 1,
214
+ "self": 188.4758612000005
215
+ },
216
+ "TrainerController.advance": {
217
+ "total": 1614.5583711996005,
218
+ "count": 63782,
219
+ "self": 1.1691986992955208,
220
+ "children": {
221
+ "env_step": {
222
+ "total": 868.3339761993266,
223
+ "count": 63782,
224
+ "self": 657.114918399704,
225
+ "children": {
226
+ "SubprocessEnvManager._take_step": {
227
+ "total": 210.47041499851912,
228
+ "count": 63782,
229
+ "self": 3.2014173990901327,
230
+ "children": {
231
+ "TorchPolicy.evaluate": {
232
+ "total": 207.26899759942899,
233
+ "count": 62570,
234
+ "self": 207.26899759942899
235
+ }
236
+ }
237
+ },
238
+ "workers": {
239
+ "total": 0.748642801103415,
240
+ "count": 63782,
241
+ "self": 0.0,
242
+ "children": {
243
+ "worker_root": {
244
+ "total": 1618.0446752017597,
245
+ "count": 63782,
246
+ "is_parallel": true,
247
+ "self": 1039.7051337024022,
248
+ "children": {
249
+ "steps_from_proto": {
250
+ "total": 0.0024889000051189214,
251
+ "count": 1,
252
+ "is_parallel": true,
253
+ "self": 0.0008089000184554607,
254
+ "children": {
255
+ "_process_rank_one_or_two_observation": {
256
+ "total": 0.0016799999866634607,
257
+ "count": 8,
258
+ "is_parallel": true,
259
+ "self": 0.0016799999866634607
260
+ }
261
+ }
262
+ },
263
+ "UnityEnvironment.step": {
264
+ "total": 578.3370525993523,
265
+ "count": 63782,
266
+ "is_parallel": true,
267
+ "self": 14.766969595308183,
268
+ "children": {
269
+ "UnityEnvironment._generate_step_input": {
270
+ "total": 12.158665203300188,
271
+ "count": 63782,
272
+ "is_parallel": true,
273
+ "self": 12.158665203300188
274
+ },
275
+ "communicator.exchange": {
276
+ "total": 504.8057025993912,
277
+ "count": 63782,
278
+ "is_parallel": true,
279
+ "self": 504.8057025993912
280
+ },
281
+ "steps_from_proto": {
282
+ "total": 46.60571520135272,
283
+ "count": 63782,
284
+ "is_parallel": true,
285
+ "self": 11.001865401573014,
286
+ "children": {
287
+ "_process_rank_one_or_two_observation": {
288
+ "total": 35.60384979977971,
289
+ "count": 510256,
290
+ "is_parallel": true,
291
+ "self": 35.60384979977971
292
+ }
293
+ }
294
+ }
295
+ }
296
+ }
297
+ }
298
+ }
299
+ }
300
+ }
301
+ }
302
+ },
303
+ "trainer_advance": {
304
+ "total": 745.0551963009784,
305
+ "count": 63782,
306
+ "self": 1.9513776992243947,
307
+ "children": {
308
+ "process_trajectory": {
309
+ "total": 123.23188330170524,
310
+ "count": 63782,
311
+ "self": 122.95206290170609,
312
+ "children": {
313
+ "RLTrainer._checkpoint": {
314
+ "total": 0.27982039999915287,
315
+ "count": 2,
316
+ "self": 0.27982039999915287
317
+ }
318
+ }
319
+ },
320
+ "_update_policy": {
321
+ "total": 619.8719353000488,
322
+ "count": 449,
323
+ "self": 291.3379866997857,
324
+ "children": {
325
+ "TorchPPOOptimizer.update": {
326
+ "total": 328.5339486002631,
327
+ "count": 22800,
328
+ "self": 328.5339486002631
329
+ }
330
+ }
331
+ }
332
+ }
333
+ }
334
+ }
335
+ },
336
+ "trainer_threads": {
337
+ "total": 6.50000583846122e-06,
338
+ "count": 1,
339
+ "self": 6.50000583846122e-06
340
+ },
341
+ "TrainerController._save_models": {
342
+ "total": 0.11670140000933316,
343
+ "count": 1,
344
+ "self": 0.02846990000398364,
345
+ "children": {
346
+ "RLTrainer._checkpoint": {
347
+ "total": 0.08823150000534952,
348
+ "count": 1,
349
+ "self": 0.08823150000534952
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ }
356
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Pyramids": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 499943,
6
+ "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-499943.onnx",
7
+ "reward": null,
8
+ "creation_time": 1713406572.0336845,
9
+ "auxillary_file_paths": [
10
+ "results\\Pyramids1\\Pyramids\\Pyramids-499943.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 999964,
15
+ "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-999964.onnx",
16
+ "reward": 1.7630000337958336,
17
+ "creation_time": 1713407403.991839,
18
+ "auxillary_file_paths": [
19
+ "results\\Pyramids1\\Pyramids\\Pyramids-999964.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 1000084,
24
+ "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-1000084.onnx",
25
+ "reward": 1.8023333301146824,
26
+ "creation_time": 1713407404.094841,
27
+ "auxillary_file_paths": [
28
+ "results\\Pyramids1\\Pyramids\\Pyramids-1000084.pt"
29
+ ]
30
+ }
31
+ ],
32
+ "final_checkpoint": {
33
+ "steps": 1000084,
34
+ "file_path": "results\\Pyramids1\\Pyramids.onnx",
35
+ "reward": 1.8023333301146824,
36
+ "creation_time": 1713407404.094841,
37
+ "auxillary_file_paths": [
38
+ "results\\Pyramids1\\Pyramids\\Pyramids-1000084.pt"
39
+ ]
40
+ }
41
+ },
42
+ "metadata": {
43
+ "stats_format_version": "0.3.0",
44
+ "mlagents_version": "1.0.0",
45
+ "torch_version": "2.2.2+cu121"
46
+ }
47
+ }