AtilliO commited on
Commit
36e8714
·
1 Parent(s): 6c944d3
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ run_logs/Player-0.log filter=lfs diff=lfs merge=lfs -text
Heli.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4990f9da334060e3dde518e65d1b3823e81e83ed5826299390cdc684d5aa64dd
3
+ size 2187053
Heli/Heli-1749584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef34302b18375070190bb463cc16913a222e07dfda442127c5f92352fc80143f
3
+ size 2187053
Heli/Heli-1749584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1785bf239e038945e3774bc3a3d02e56cd73f254907779d52e98ff4668f35a71
3
+ size 14922498
Heli/Heli-1999584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5b6ee7cd33561db07ba82811ec24e7c45a910105ff6118e6219be3b843d9ab
3
+ size 2187053
Heli/Heli-1999584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb97b37443881415f366fd2104385c1bd6db3b3c0d5fea4b7bcef2c63d24995a
3
+ size 14922498
Heli/Heli-2249584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c52a2453304fb1bf07934f4e9fced6f83a1781fb04d44e72e606eba2d3a46ad
3
+ size 2187053
Heli/Heli-2249584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c48992d1ccf566629d4253ef5d75f7144f74c8feceaef3bf2b3b9861c35df0
3
+ size 14922498
Heli/Heli-2499584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9211db582ad52230c04524fe6a2dbdd031b439c31437af9175354a04fd002732
3
+ size 2187053
Heli/Heli-2499584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7458e4bb1c064241e135d27326902d4d616c062a2e383412354796d11b9ea8
3
+ size 14922498
Heli/Heli-2749584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbba04429808c98137cc9a16825e09c55a6de8a2f3f931fd6ab77862d0b866a
3
+ size 2187053
Heli/Heli-2749584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab15a8e6ef037b3de6c8eea834a29e463f709acca9dea95c3412ad03665cfd7
3
+ size 14922498
Heli/Heli-2999584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca1981e1b341fac553efa0acea1c608592a7eaea0f74928053e05a6d755b8ec
3
+ size 2187053
Heli/Heli-2999584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b995fc3cebe5c620d9ea9064dcb46562cec5ca39a70be81276153064c34ce216
3
+ size 14922498
Heli/Heli-3249584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06519129d536de64569a1da25a05a5b205848df6c95155a4044149fa7784888
3
+ size 2187053
Heli/Heli-3249584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430402f2a1df9d859320a92b02da70fea1f9da019bcc49edb5caa13e0ab825dd
3
+ size 14922498
Heli/Heli-3499584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce1287f156605bab1247ce31616bcb20fc3029b60f4df1af99ba5f68fbf7a5a
3
+ size 2187053
Heli/Heli-3499584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8412d554b4f47de10f1e9afa29ad079b43c1c5c479c24c1c95d1f16a5ed03db
3
+ size 14922498
Heli/Heli-3749584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0014ea3fd60b060bd93d885291ac5895bf3d8afc7560d2a5738f8350d1131af9
3
+ size 2187053
Heli/Heli-3749584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790f5fd7546e59c520576901275ecf75e5928c88cc676144155779eb3a21c2aa
3
+ size 14922498
Heli/Heli-3999584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a1e4280661bd779d3c09100c797b4559cf70007a9e9ea28f012553530043b3
3
+ size 2187053
Heli/Heli-3999584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8107fbd5d1e7fbfa06a2d5b791f452d3e3bfd338d71aed7f56879ff074e4eb10
3
+ size 14922498
Heli/Heli-4249584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3085bae8827906a618be84e4cab9806bddeedbd501060b82be1ba502fffa350a
3
+ size 2187053
Heli/Heli-4249584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8630ee91299f84d89fd88c0f687b4eac731bf87fe03cff2f0581ccb3d27dc40
3
+ size 14922498
Heli/Heli-4499584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1375ab364d8b11d18a0667a8934986c05cc56e12f8de3372be9f2f2bcd9b2e
3
+ size 2187053
Heli/Heli-4499584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdef44c62a76033437706eec8d76f9343cae81696f897b8620f4cd2f819c899e
3
+ size 14922498
Heli/Heli-4749584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5654f3d0c13bb36303664859fc771e4b04c0981ae037120cb189b22f4a2b5a
3
+ size 2187053
Heli/Heli-4749584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77be9fe84097ce811e7454551d617c7aa82a0453748fb6d9fdbd78fac4a4a145
3
+ size 14922498
Heli/Heli-4999584.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e27414d6f5b8aea59ca1a0eeaf1691d763b56d20f02ab018533dc4ba3faada7
3
+ size 2187053
Heli/Heli-4999584.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26eb597f3fd8bdfe4b2eda44020fcbfca7985bd959de161a392d4376a7bbc1f5
3
+ size 14922498
Heli/Heli-5005721.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4990f9da334060e3dde518e65d1b3823e81e83ed5826299390cdc684d5aa64dd
3
+ size 2187053
Heli/Heli-5005721.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7fdea72da932a6a8542ff93aad885448326f400f965bbb68b5f6e47b8022a9
3
+ size 14922498
Heli/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7fdea72da932a6a8542ff93aad885448326f400f965bbb68b5f6e47b8022a9
3
+ size 14922498
Heli/events.out.tfevents.1691442043.w-xitxa-mla4-a057a30e8f5c4ff38a9835cb6c7593ce-677cb7846-x7wb9.548.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619b32cbdd1129f1b853cacf33e0027dbeefc0414a7c5990b40ff74165f48bad
3
+ size 1158757
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - Heli
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-Heli
8
+ ---
9
+
10
+ # **ppo** Agent playing **Heli**
11
+ This is a trained model of a **ppo** agent playing **Heli**
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: AtilliO/Chopper03_00
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": {"Heli": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 10240, "learning_rate": 0.0002, "beta": 0.001, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 250000, "network_settings": {"normalize": true, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 512, "summary_freq": 5000, "threaded": true, "self_play": null, "behavioral_cloning": null}, "LoaderG": {"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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 512, "summary_freq": 5000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/ChopperLnx03/ChopperLnx03", "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": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Chopper03_00", "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 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Heli:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 256
7
+ buffer_size: 10240
8
+ learning_rate: 0.0002
9
+ beta: 0.001
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: 250000
18
+ network_settings:
19
+ normalize: true
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
+ curiosity:
39
+ gamma: 0.99
40
+ strength: 0.02
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 256
44
+ num_layers: 2
45
+ vis_encode_type: simple
46
+ memory: null
47
+ goal_conditioning_type: hyper
48
+ deterministic: false
49
+ learning_rate: 0.0003
50
+ encoding_size: null
51
+ init_path: null
52
+ keep_checkpoints: 15
53
+ even_checkpoints: false
54
+ max_steps: 5000000
55
+ time_horizon: 512
56
+ summary_freq: 5000
57
+ threaded: true
58
+ self_play: null
59
+ behavioral_cloning: null
60
+ LoaderG:
61
+ trainer_type: ppo
62
+ hyperparameters:
63
+ batch_size: 128
64
+ buffer_size: 2048
65
+ learning_rate: 0.0003
66
+ beta: 0.01
67
+ epsilon: 0.2
68
+ lambd: 0.95
69
+ num_epoch: 3
70
+ shared_critic: false
71
+ learning_rate_schedule: linear
72
+ beta_schedule: linear
73
+ epsilon_schedule: linear
74
+ checkpoint_interval: 500000
75
+ network_settings:
76
+ normalize: false
77
+ hidden_units: 512
78
+ num_layers: 2
79
+ vis_encode_type: simple
80
+ memory: null
81
+ goal_conditioning_type: hyper
82
+ deterministic: false
83
+ reward_signals:
84
+ extrinsic:
85
+ gamma: 0.99
86
+ strength: 1.0
87
+ network_settings:
88
+ normalize: false
89
+ hidden_units: 128
90
+ num_layers: 2
91
+ vis_encode_type: simple
92
+ memory: null
93
+ goal_conditioning_type: hyper
94
+ deterministic: false
95
+ curiosity:
96
+ gamma: 0.99
97
+ strength: 0.02
98
+ network_settings:
99
+ normalize: false
100
+ hidden_units: 256
101
+ num_layers: 2
102
+ vis_encode_type: simple
103
+ memory: null
104
+ goal_conditioning_type: hyper
105
+ deterministic: false
106
+ learning_rate: 0.0003
107
+ encoding_size: null
108
+ init_path: null
109
+ keep_checkpoints: 5
110
+ even_checkpoints: false
111
+ max_steps: 2000000
112
+ time_horizon: 512
113
+ summary_freq: 5000
114
+ threaded: true
115
+ self_play: null
116
+ behavioral_cloning: null
117
+ env_settings:
118
+ env_path: ./training-envs-executables/linux/ChopperLnx03/ChopperLnx03
119
+ env_args: null
120
+ base_port: 5005
121
+ num_envs: 1
122
+ num_areas: 1
123
+ seed: -1
124
+ max_lifetime_restarts: 10
125
+ restarts_rate_limit_n: 1
126
+ restarts_rate_limit_period_s: 60
127
+ engine_settings:
128
+ width: 84
129
+ height: 84
130
+ quality_level: 5
131
+ time_scale: 20
132
+ target_frame_rate: -1
133
+ capture_frame_rate: 60
134
+ no_graphics: true
135
+ environment_parameters: null
136
+ checkpoint_settings:
137
+ run_id: Chopper03_00
138
+ initialize_from: null
139
+ load_model: false
140
+ resume: false
141
+ force: false
142
+ train_model: false
143
+ inference: false
144
+ results_dir: results
145
+ torch_settings:
146
+ device: null
147
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f9062b1f04b664bc57e6ef2e70b9ec66eb9a7f23b45551c77738792b9b8804
3
+ size 69423031
run_logs/timers.json ADDED
@@ -0,0 +1,425 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Heli.Policy.Entropy.mean": {
5
+ "value": 0.39192596077919006,
6
+ "min": 0.39192596077919006,
7
+ "max": 4.393238067626953,
8
+ "count": 1001
9
+ },
10
+ "Heli.Policy.Entropy.sum": {
11
+ "value": 21.947853088378906,
12
+ "min": 21.947853088378906,
13
+ "max": 43042.21875,
14
+ "count": 1001
15
+ },
16
+ "Heli.Environment.EpisodeLength.mean": {
17
+ "value": 624.0,
18
+ "min": 293.11764705882354,
19
+ "max": 624.0,
20
+ "count": 931
21
+ },
22
+ "Heli.Environment.EpisodeLength.sum": {
23
+ "value": 10608.0,
24
+ "min": 624.0,
25
+ "max": 11232.0,
26
+ "count": 931
27
+ },
28
+ "Heli.Step.mean": {
29
+ "value": 5004584.0,
30
+ "min": 4516.0,
31
+ "max": 5004584.0,
32
+ "count": 1001
33
+ },
34
+ "Heli.Step.sum": {
35
+ "value": 5004584.0,
36
+ "min": 4516.0,
37
+ "max": 5004584.0,
38
+ "count": 1001
39
+ },
40
+ "Heli.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.1655795574188232,
42
+ "min": -0.28883567452430725,
43
+ "max": 2.3287107944488525,
44
+ "count": 1001
45
+ },
46
+ "Heli.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 34.64927291870117,
48
+ "min": -5.199042320251465,
49
+ "max": 37.25937271118164,
50
+ "count": 1001
51
+ },
52
+ "Heli.Policy.CuriosityValueEstimate.mean": {
53
+ "value": 0.0259267408400774,
54
+ "min": 0.016802363097667694,
55
+ "max": 0.6830515265464783,
56
+ "count": 1001
57
+ },
58
+ "Heli.Policy.CuriosityValueEstimate.sum": {
59
+ "value": 0.4148278534412384,
60
+ "min": 0.2688378095626831,
61
+ "max": 10.928824424743652,
62
+ "count": 1001
63
+ },
64
+ "Heli.Environment.CumulativeReward.mean": {
65
+ "value": 13.689250871539116,
66
+ "min": -31.835629977285862,
67
+ "max": 15.341751277446747,
68
+ "count": 1001
69
+ },
70
+ "Heli.Environment.CumulativeReward.sum": {
71
+ "value": 109.51400697231293,
72
+ "min": -509.3700796365738,
73
+ "max": 122.73401021957397,
74
+ "count": 1001
75
+ },
76
+ "Heli.Policy.ExtrinsicReward.mean": {
77
+ "value": 13.689250871539116,
78
+ "min": -31.835629977285862,
79
+ "max": 15.341751277446747,
80
+ "count": 1001
81
+ },
82
+ "Heli.Policy.ExtrinsicReward.sum": {
83
+ "value": 109.51400697231293,
84
+ "min": -509.3700796365738,
85
+ "max": 122.73401021957397,
86
+ "count": 1001
87
+ },
88
+ "Heli.Policy.CuriosityReward.mean": {
89
+ "value": 0.21203715912997723,
90
+ "min": 0.0,
91
+ "max": 18.772306240521946,
92
+ "count": 1001
93
+ },
94
+ "Heli.Policy.CuriosityReward.sum": {
95
+ "value": 1.6962972730398178,
96
+ "min": 0.0,
97
+ "max": 244.03998112678528,
98
+ "count": 1001
99
+ },
100
+ "Heli.IsTraining.mean": {
101
+ "value": 0.0,
102
+ "min": 0.0,
103
+ "max": 1.0,
104
+ "count": 1001
105
+ },
106
+ "Heli.IsTraining.sum": {
107
+ "value": 0.0,
108
+ "min": 0.0,
109
+ "max": 1.0,
110
+ "count": 1001
111
+ },
112
+ "Heli.Losses.PolicyLoss.mean": {
113
+ "value": 0.04507838136410507,
114
+ "min": 0.03936668122717278,
115
+ "max": 0.05903104245776265,
116
+ "count": 471
117
+ },
118
+ "Heli.Losses.PolicyLoss.sum": {
119
+ "value": 0.04507838136410507,
120
+ "min": 0.03936668122717278,
121
+ "max": 0.05903104245776265,
122
+ "count": 471
123
+ },
124
+ "Heli.Losses.ValueLoss.mean": {
125
+ "value": 5.077333335657756e-06,
126
+ "min": 3.696700387968676e-06,
127
+ "max": 0.5923735979126721,
128
+ "count": 471
129
+ },
130
+ "Heli.Losses.ValueLoss.sum": {
131
+ "value": 5.077333335657756e-06,
132
+ "min": 3.696700387968676e-06,
133
+ "max": 0.5923735979126721,
134
+ "count": 471
135
+ },
136
+ "Heli.Policy.LearningRate.mean": {
137
+ "value": 2.125998942000895e-08,
138
+ "min": 2.125998942000895e-08,
139
+ "max": 0.00019957072021464006,
140
+ "count": 471
141
+ },
142
+ "Heli.Policy.LearningRate.sum": {
143
+ "value": 2.125998942000895e-08,
144
+ "min": 2.125998942000895e-08,
145
+ "max": 0.00019957072021464006,
146
+ "count": 471
147
+ },
148
+ "Heli.Policy.Epsilon.mean": {
149
+ "value": 0.10001057999999996,
150
+ "min": 0.10001057999999996,
151
+ "max": 0.19978535999999997,
152
+ "count": 471
153
+ },
154
+ "Heli.Policy.Epsilon.sum": {
155
+ "value": 0.10001057999999996,
156
+ "min": 0.10001057999999996,
157
+ "max": 0.19978535999999997,
158
+ "count": 471
159
+ },
160
+ "Heli.Policy.Beta.mean": {
161
+ "value": 1.0104742000000044e-05,
162
+ "min": 1.0104742000000044e-05,
163
+ "max": 0.000997875064,
164
+ "count": 471
165
+ },
166
+ "Heli.Policy.Beta.sum": {
167
+ "value": 1.0104742000000044e-05,
168
+ "min": 1.0104742000000044e-05,
169
+ "max": 0.000997875064,
170
+ "count": 471
171
+ },
172
+ "Heli.Losses.CuriosityForwardLoss.mean": {
173
+ "value": 0.012605215013935798,
174
+ "min": 0.011452520788624519,
175
+ "max": 883.8118460158992,
176
+ "count": 471
177
+ },
178
+ "Heli.Losses.CuriosityForwardLoss.sum": {
179
+ "value": 0.012605215013935798,
180
+ "min": 0.011452520788624519,
181
+ "max": 883.8118460158992,
182
+ "count": 471
183
+ },
184
+ "Heli.Losses.CuriosityInverseLoss.mean": {
185
+ "value": 0.559255926831951,
186
+ "min": 0.5118315958879828,
187
+ "max": 5.3319927696290055,
188
+ "count": 471
189
+ },
190
+ "Heli.Losses.CuriosityInverseLoss.sum": {
191
+ "value": 0.559255926831951,
192
+ "min": 0.5118315958879828,
193
+ "max": 5.3319927696290055,
194
+ "count": 471
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1691442042",
200
+ "python_version": "3.9.15 | packaged by conda-forge | (main, Nov 22 2022, 08:45:29) \n[GCC 10.4.0]",
201
+ "command_line_arguments": "/opt/saturncloud/envs/saturn/bin/mlagents-learn ./config/ppo/Beach.yaml --env=./training-envs-executables/linux/ChopperLnx03/ChopperLnx03 --run-id=Chopper03_00 --no-graphics",
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+cu102",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1691460247"
208
+ },
209
+ "total": 18205.520656685,
210
+ "count": 1,
211
+ "self": 0.5429026519996114,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.0698934439999448,
215
+ "count": 1,
216
+ "self": 0.0698934439999448
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 18204.907860589,
220
+ "count": 1,
221
+ "self": 38.8902137390578,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 0.8747101139999813,
225
+ "count": 1,
226
+ "self": 0.8747101139999813
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 18164.883307811942,
230
+ "count": 1259581,
231
+ "self": 19.638242822802567,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 18145.24506498914,
235
+ "count": 1259581,
236
+ "self": 12095.953272106115,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 6029.319874835739,
240
+ "count": 1259581,
241
+ "self": 95.90401423651019,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 5933.415860599229,
245
+ "count": 1251674,
246
+ "self": 5933.415860599229
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 19.971918047284817,
252
+ "count": 1259581,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 18136.52002106727,
257
+ "count": 1259581,
258
+ "is_parallel": true,
259
+ "self": 8838.47566039592,
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": 0.0014940669998395606,
269
+ "count": 1,
270
+ "is_parallel": true,
271
+ "self": 0.00046801799999229843,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0010260489998472622,
275
+ "count": 6,
276
+ "is_parallel": true,
277
+ "self": 0.0010260489998472622
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.055272845999979836,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0003079680002429086,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00023928799987515958,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.00023928799987515958
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.05352719999996225,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.05352719999996225
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0011983899998995184,
301
+ "count": 1,
302
+ "is_parallel": true,
303
+ "self": 0.00034328499964431103,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0008551050002552074,
307
+ "count": 6,
308
+ "is_parallel": true,
309
+ "self": 0.0008551050002552074
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 9298.04436067135,
319
+ "count": 1259580,
320
+ "is_parallel": true,
321
+ "self": 351.7882387268837,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 212.84615533905867,
325
+ "count": 1259580,
326
+ "is_parallel": true,
327
+ "self": 212.84615533905867
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 7401.790050097831,
331
+ "count": 1259580,
332
+ "is_parallel": true,
333
+ "self": 7401.790050097831
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 1331.619916507577,
337
+ "count": 1259580,
338
+ "is_parallel": true,
339
+ "self": 373.7393082039507,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 957.8806083036263,
343
+ "count": 7557480,
344
+ "is_parallel": true,
345
+ "self": 957.8806083036263
346
+ }
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ },
359
+ "trainer_threads": {
360
+ "total": 0.011040366000088397,
361
+ "count": 1,
362
+ "self": 0.011040366000088397,
363
+ "children": {
364
+ "thread_root": {
365
+ "total": 0.0,
366
+ "count": 0,
367
+ "is_parallel": true,
368
+ "self": 0.0,
369
+ "children": {
370
+ "trainer_advance": {
371
+ "total": 18110.851568129834,
372
+ "count": 9656543,
373
+ "is_parallel": true,
374
+ "self": 247.31906628051001,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 6399.8019213723455,
378
+ "count": 9656543,
379
+ "is_parallel": true,
380
+ "self": 6392.765605778344,
381
+ "children": {
382
+ "RLTrainer._checkpoint": {
383
+ "total": 7.0363155940008255,
384
+ "count": 20,
385
+ "is_parallel": true,
386
+ "self": 7.0363155940008255
387
+ }
388
+ }
389
+ },
390
+ "_update_policy": {
391
+ "total": 11463.730580476979,
392
+ "count": 471,
393
+ "is_parallel": true,
394
+ "self": 6411.6264944578,
395
+ "children": {
396
+ "TorchPPOOptimizer.update": {
397
+ "total": 5052.104086019179,
398
+ "count": 57900,
399
+ "is_parallel": true,
400
+ "self": 5052.104086019179
401
+ }
402
+ }
403
+ }
404
+ }
405
+ }
406
+ }
407
+ }
408
+ }
409
+ },
410
+ "TrainerController._save_models": {
411
+ "total": 0.24858855799902813,
412
+ "count": 1,
413
+ "self": 0.0017533809987071436,
414
+ "children": {
415
+ "RLTrainer._checkpoint": {
416
+ "total": 0.24683517700032098,
417
+ "count": 1,
418
+ "self": 0.24683517700032098
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
425
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Heli": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 1749584,
6
+ "file_path": "results/Chopper03_00/Heli/Heli-1749584.onnx",
7
+ "reward": 13.256501078605652,
8
+ "creation_time": 1691448423.68727,
9
+ "auxillary_file_paths": [
10
+ "results/Chopper03_00/Heli/Heli-1749584.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 1999584,
15
+ "file_path": "results/Chopper03_00/Heli/Heli-1999584.onnx",
16
+ "reward": 13.321000943581263,
17
+ "creation_time": 1691449302.9643607,
18
+ "auxillary_file_paths": [
19
+ "results/Chopper03_00/Heli/Heli-1999584.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 2249584,
24
+ "file_path": "results/Chopper03_00/Heli/Heli-2249584.onnx",
25
+ "reward": 13.34500116109848,
26
+ "creation_time": 1691450209.9572675,
27
+ "auxillary_file_paths": [
28
+ "results/Chopper03_00/Heli/Heli-2249584.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 2499584,
33
+ "file_path": "results/Chopper03_00/Heli/Heli-2499584.onnx",
34
+ "reward": 13.569847198633047,
35
+ "creation_time": 1691451092.3893976,
36
+ "auxillary_file_paths": [
37
+ "results/Chopper03_00/Heli/Heli-2499584.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 2749584,
42
+ "file_path": "results/Chopper03_00/Heli/Heli-2749584.onnx",
43
+ "reward": 14.011601161956786,
44
+ "creation_time": 1691452011.6956503,
45
+ "auxillary_file_paths": [
46
+ "results/Chopper03_00/Heli/Heli-2749584.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 2999584,
51
+ "file_path": "results/Chopper03_00/Heli/Heli-2999584.onnx",
52
+ "reward": 13.399201027552287,
53
+ "creation_time": 1691452905.6002686,
54
+ "auxillary_file_paths": [
55
+ "results/Chopper03_00/Heli/Heli-2999584.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 3249584,
60
+ "file_path": "results/Chopper03_00/Heli/Heli-3249584.onnx",
61
+ "reward": 13.605143870626177,
62
+ "creation_time": 1691453844.3030002,
63
+ "auxillary_file_paths": [
64
+ "results/Chopper03_00/Heli/Heli-3249584.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 3499584,
69
+ "file_path": "results/Chopper03_00/Heli/Heli-3499584.onnx",
70
+ "reward": 13.87900085002184,
71
+ "creation_time": 1691454730.371976,
72
+ "auxillary_file_paths": [
73
+ "results/Chopper03_00/Heli/Heli-3499584.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 3749584,
78
+ "file_path": "results/Chopper03_00/Heli/Heli-3749584.onnx",
79
+ "reward": 13.893750742077827,
80
+ "creation_time": 1691455641.2139494,
81
+ "auxillary_file_paths": [
82
+ "results/Chopper03_00/Heli/Heli-3749584.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 3999584,
87
+ "file_path": "results/Chopper03_00/Heli/Heli-3999584.onnx",
88
+ "reward": 13.990125931799412,
89
+ "creation_time": 1691456535.2560039,
90
+ "auxillary_file_paths": [
91
+ "results/Chopper03_00/Heli/Heli-3999584.pt"
92
+ ]
93
+ },
94
+ {
95
+ "steps": 4249584,
96
+ "file_path": "results/Chopper03_00/Heli/Heli-4249584.onnx",
97
+ "reward": 14.129001080989838,
98
+ "creation_time": 1691457478.282172,
99
+ "auxillary_file_paths": [
100
+ "results/Chopper03_00/Heli/Heli-4249584.pt"
101
+ ]
102
+ },
103
+ {
104
+ "steps": 4499584,
105
+ "file_path": "results/Chopper03_00/Heli/Heli-4499584.onnx",
106
+ "reward": 14.108824512537788,
107
+ "creation_time": 1691458376.4700978,
108
+ "auxillary_file_paths": [
109
+ "results/Chopper03_00/Heli/Heli-4499584.pt"
110
+ ]
111
+ },
112
+ {
113
+ "steps": 4749584,
114
+ "file_path": "results/Chopper03_00/Heli/Heli-4749584.onnx",
115
+ "reward": 14.099112113316854,
116
+ "creation_time": 1691459301.522446,
117
+ "auxillary_file_paths": [
118
+ "results/Chopper03_00/Heli/Heli-4749584.pt"
119
+ ]
120
+ },
121
+ {
122
+ "steps": 4999584,
123
+ "file_path": "results/Chopper03_00/Heli/Heli-4999584.onnx",
124
+ "reward": 15.556000709533691,
125
+ "creation_time": 1691460246.5216184,
126
+ "auxillary_file_paths": [
127
+ "results/Chopper03_00/Heli/Heli-4999584.pt"
128
+ ]
129
+ },
130
+ {
131
+ "steps": 5005721,
132
+ "file_path": "results/Chopper03_00/Heli/Heli-5005721.onnx",
133
+ "reward": 14.076200830936433,
134
+ "creation_time": 1691460247.420439,
135
+ "auxillary_file_paths": [
136
+ "results/Chopper03_00/Heli/Heli-5005721.pt"
137
+ ]
138
+ }
139
+ ],
140
+ "final_checkpoint": {
141
+ "steps": 5005721,
142
+ "file_path": "results/Chopper03_00/Heli.onnx",
143
+ "reward": 14.076200830936433,
144
+ "creation_time": 1691460247.420439,
145
+ "auxillary_file_paths": [
146
+ "results/Chopper03_00/Heli/Heli-5005721.pt"
147
+ ]
148
+ }
149
+ },
150
+ "metadata": {
151
+ "stats_format_version": "0.3.0",
152
+ "mlagents_version": "0.31.0.dev0",
153
+ "torch_version": "1.11.0+cu102"
154
+ }
155
+ }