Reinforcement learning algorithms in RLlib and PyTorch.
Project description
raylab
Reinforcement learning algorithms in RLlib and PyTorch.
Introduction
Raylab provides agents and environments to be used with a normal RLlib/Tune setup.
import ray
from ray import tune
import raylab
def main():
raylab.register_all_agents()
raylab.register_all_environments()
ray.init()
tune.run(
"NAF",
local_dir=...,
stop={"timesteps_total": 100000},
config={
"env": "CartPoleSwingUp-v0",
"exploration_config": {
"type": tune.grid_search([
"raylab.utils.exploration.GaussianNoise",
"raylab.utils.exploration.ParameterNoise"
])
}
...
},
)
if __name__ == "__main__":
main()
One can then visualize the results using raylab dashboard
Installation
pip install raylab
Algorithms
Paper |
Agent Name |
ACKTR |
|
TRPO |
|
NAF |
|
SVG(inf)/SVG(1)/SoftSVG |
|
SoftAC |
|
Streamlined Off-Policy (DDPG) |
SOP |
Command-line interface
For a high-level description of the available utilities, run raylab –help
Usage: raylab [OPTIONS] COMMAND [ARGS]...
RayLab: Reinforcement learning algorithms in RLlib.
Options:
--help Show this message and exit.
Commands:
dashboard Launch the experiment dashboard to monitor training progress.
experiment Launch a Tune experiment from a config file.
find-best Find the best experiment checkpoint as measured by a metric.
plot Draw lineplots of the relevant variables and display them on...
plot-export Draw lineplots of the relevant variables and save them as...
rollout Simulate an agent from a given checkpoint in the desired...
Packages
The project is structured as follows
raylab ├── agents # Trainer and Policy classes ├── cli # Command line utilities ├── distributions # Extendend and additional PyTorch distributions ├── envs # Gym environments ├── logger # Tune loggers ├── modules # PyTorch neural network modules for algorithms ├── basic # Building blocks for neural networks ├── flows # Normalizing Flow modules ├── distributions # TorchScript compatible distribution modules ├── policy # Extensions and customizations of RLlib's policy API ├── utils # miscellaneous utilities
Credits
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
History
0.6.5 (2020-05-21)
First release on PyPI.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
raylab-0.6.7.tar.gz
(128.5 kB
view hashes)