chradden commited on
Commit
6a45457
·
1 Parent(s): f84df0b

First Push

Browse files
Pyramids-1000098.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d335721b7f6443131d7670ff08184dd6cd9c2523b6d328c228673bffdfbed6b
3
+ size 1418184
Pyramids-1000098.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd1e4849194d4176c2f0123c673493d2ed690ba7d4e4f199e2f05a134fe36af
3
+ size 8650990
Pyramids-499902.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffbde6f5478aca1f98633b07e3546b28170d78dd6aa20e6050369c63f45e97f
3
+ size 1418184
Pyramids-499902.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5a01062dc2dd273c6167244228333a33b638a4a60bf9224abeb127090954dd
3
+ size 8650990
Pyramids-999986.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d335721b7f6443131d7670ff08184dd6cd9c2523b6d328c228673bffdfbed6b
3
+ size 1418184
Pyramids-999986.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d87ddc60af1abe28170e2fdeb514c3e31466f1638262cfdc9310e1cc662b6e4
3
+ size 8650990
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
12
+
13
+ ## Usage (with ML-Agents)
14
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
15
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
16
+
17
+
18
+ ### Resume the training
19
+ ```
20
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
21
+ ```
22
+ ### Watch your Agent play
23
+ You can watch your agent **playing directly in your browser:**.
24
+
25
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
26
+ 2. Step 1: Find your model_id: chradden/Pyramids
27
+ 3. Step 2: Select your *.nn /*.onnx file
28
+ 4. Click on Watch the agent play 👀
29
+
checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd1e4849194d4176c2f0123c673493d2ed690ba7d4e4f199e2f05a134fe36af
3
+ size 8650990
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": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids Training", "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 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ./training-envs-executables/linux/Pyramids/Pyramids
62
+ env_args: null
63
+ base_port: 5005
64
+ num_envs: 1
65
+ num_areas: 1
66
+ seed: -1
67
+ max_lifetime_restarts: 10
68
+ restarts_rate_limit_n: 1
69
+ restarts_rate_limit_period_s: 60
70
+ engine_settings:
71
+ width: 84
72
+ height: 84
73
+ quality_level: 5
74
+ time_scale: 20
75
+ target_frame_rate: -1
76
+ capture_frame_rate: 60
77
+ no_graphics: true
78
+ environment_parameters: null
79
+ checkpoint_settings:
80
+ run_id: Pyramids Training
81
+ initialize_from: null
82
+ load_model: false
83
+ resume: false
84
+ force: false
85
+ train_model: false
86
+ inference: false
87
+ results_dir: results
88
+ torch_settings:
89
+ device: null
90
+ debug: false
events.out.tfevents.1679677590.1e68e03a1426.16003.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1604e0ebcf5d23fd4b2b9f87064579cba4fb190f471b26d727b7bb0a5df48e6
3
+ size 295378