Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use harkrishkali/ppo-Pyramid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use harkrishkali/ppo-Pyramid with ml-agents:
mlagents-load-from-hf --repo-id="harkrishkali/ppo-Pyramid" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Upload 3 files
Browse files- Pyramids.onnx +3 -0
- config.json +1 -0
- configuration.yaml +92 -0
Pyramids.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee24402646c1948a0afc7fb1a7e4fb832c084d01bd9fc959a4ee6f0bcec5b50
|
| 3 |
+
size 1420238
|
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": 300000, "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, "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": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "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 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 300000
|
| 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 |
+
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: true
|
| 79 |
+
no_graphics_monitor: false
|
| 80 |
+
environment_parameters: null
|
| 81 |
+
checkpoint_settings:
|
| 82 |
+
run_id: Pyramids Training
|
| 83 |
+
initialize_from: null
|
| 84 |
+
load_model: false
|
| 85 |
+
resume: false
|
| 86 |
+
force: true
|
| 87 |
+
train_model: false
|
| 88 |
+
inference: false
|
| 89 |
+
results_dir: results
|
| 90 |
+
torch_settings:
|
| 91 |
+
device: null
|
| 92 |
+
debug: false
|