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.

Source Distribution

RLkit-0.2.0.tar.gz (6.2 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page