Skip to main content

A simple RL library.

Project description

RLkit: A simple Reinforcement Learning library

This project is still a work in progress. More algorithms and detailed documentation coming soon :)

Currently supported agents-

  1. Random agent
  2. REINFORCE (Policy Gradients)
  3. DQN
  4. DQN with baseline
  5. Actor-Critic

See examples for details on how to use the library.

Requirements-

tensorflow==1.11.0
gym==0.10.8
numpy==1.15.4

New in v0.2

  • Added DQN and DQN with baseline agents
  • Added ActorCritic agent
  • Added support for various activation functions

Upcoming

  • Duelling DQN
  • Support for logging and plotting
  • Support for adding seeds
  • Support for custom environments

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 RLkit, version 0.2.0
Filename, size & hash File type Python version Upload date
RLkit-0.2.0.tar.gz (6.2 kB) View hashes Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page