Deep Reinforcement Learning for the JVM
Java Shell
Latest commit bf289f3 Feb 24, 2017 @saudet saudet committed on GitHub Update dependency on JavaCV to version 1.3.1 (pull #23)

README.md

RL4J

Reinforcement learning framework integrated with deeplearning4j.

  • DQN (Deep Q Learning with double DQN)
  • Async RL (A3C, Async NStepQlearning)

Both for Low-Dimensional (array of info) and high-dimensional (pixels) input.

DOOM

Cartpole

Here is a useful blog post I wrote to introduce you to reinforcement learning, DQN and Async RL:

Blog post

temporary example repo

Cartpole example

Disclaimer

This is a tech preview and distributed as is. Comments are welcome on our gitter channel: gitter

Quickstart

** INSTALL rl4j-api before installing all (see below)!**

  • mvn install -pl rl4j-api
  • [if you want rl4j-gym too] Download and mvn install: gym-java-client
  • mvn install

Visualisation

webapp-rl4j

Quicktry cartpole:

Doom

Doom is not ready yet but you can make it work if you feel adventurous with some additional steps:

  • You will need vizdoom, compile the native lib and move it into the root of your project in a folder
  • export MAVEN_OPTS=-Djava.library.path=THEFOLDEROFTHELIB
  • mvn compile exec:java -Dexec.mainClass="YOURMAINCLASS"

WIP

  • Documentation
  • Serialization/Deserialization (load save)
  • Compression of pixels in order to store 1M state in a reasonnable amount of memory
  • Async learning: A3C and nstep learning (requires some missing features from dl4j (calc and apply gradients)).

Author

Ruben Fiszel

Proposed contribution area:

  • Continuous control
  • Policy Gradient
  • Update gym-java-client when gym-http-api gets compatible with pixels environments to play with Pong, Doom, etc ..