Skip to main content

A package to learn about Reinforcement Learning

Project description

About LearnRL

LearnRL is a librairie to use and learn reinforcement learning.
Look how easy it is to use:
import learnrl as rl
from learnrl.environments import CrossesAndNoughtsEnv
from learnrl.agents import TableAgent

env = CrossesAndNoughtsEnv()
agent1 = TableAgent(state_space=env.observation_space, action_space=env.action_space)
agent2 = TableAgent(state_space=env.observation_space, action_space=env.action_space)

agents = [agent1, agent2]
pg = rl.Playground(env, agents)
pg.fit(50000, verbose=1)

And boom you made two QLearning AIs training against each other on crosses and noughts !

Features

  • Build highly configurable classic reinforcement learning agents in few lines of code
  • Train your Agents on any Gym environments
  • Use this API to create your own agents and environments (even multiplayer!) with great compatibility

Installation

Install LearnRL by running:

pip install learnrl

Documentation

See the latest complete documentation for more details

Contribute

Support

If you are having issues, please let me know at mathfederico@gmail.com

License

The project is licensed under the GNU LGPLv3 license.
See LICENCE, COPYING and COPYING.LESSER for more details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for learnrl, version 0.1.1
Filename, size File type Python version Upload date Hashes
Filename, size learnrl-0.1.1-py3-none-any.whl (54.2 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size learnrl-0.1.1.tar.gz (21.8 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page