cavis/rl4j
Alexandre Boulanger 59f1cbf0c6 RL4J - AsyncTrainingListener (#8072)
* Code clarity: Extracted parts of run() into private methods

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Added listener pattern to async learning

Signed-off-by: unknown <aboulang2002@yahoo.com>

* Merged all listeners logic

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Added interface and common data to training events

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Fixed missing info log file

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Fixed bad merge; removed useless TrainingEvent

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Removed param from training start/end event

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Removed 'event' classes from the training listener

Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com>

* Reverted changes to QLearningDiscrete.setTarget()
2019-09-19 11:28:13 +10:00
..
contrib Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
rl4j-ale Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
rl4j-api Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
rl4j-core RL4J - AsyncTrainingListener (#8072) 2019-09-19 11:28:13 +10:00
rl4j-doom Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
rl4j-gym Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
rl4j-malmo Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
LICENSE.txt Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
README.md Update links to eclipse repos (#252) 2019-09-10 19:09:46 +10:00
cartpole.gif Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
doom.gif Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
malmo.gif Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
pom.xml Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00
scoregraph.png Eclipse Migration Initial Commit 2019-06-06 15:21:15 +03:00

README.md

RL4J: Reinforcement Learning for Java

RL4J is a reinforcement learning framework integrated with deeplearning4j and released under an Apache 2.0 open-source license. By contributing code to this repository, you agree to make your contribution available under an Apache 2.0 license.

  • 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

Examples

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"

Malmo (Minecraft)

Malmo

  • Download and unzip Malmo from here
  • export MALMO_HOME=YOURMALMO_FOLDER
  • export MALMO_XSD_PATH=$MALMO_HOME/Schemas
  • launch malmo per instructions
  • run with this main

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 ..