DaomingLyu / RRL

supplementary code for paper "Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

For each experiment there is a corresponding folder including a readme file with the instruction to run that experiment.

Everything has been tested on Tensorflow 1.15 and python 3.6

IMNPORTANT *** The new TF. 2.3 implementation of codes are available in subfolder TF_VER2 

Libraries :
Tensorflow-gpu
numpy
pandas
gym
stable_baselines ( only needed for the A2C baseline comnparison, it is not needed for our own models. )

About

supplementary code for paper "Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming"


Languages

Language:Python 100.0%