markdumke/reinforceR: Reinforcement Learning

Implements reinforcement learning environments and algorithms as described in Sutton & Barto (1998, ISBN:0262193981). The Q-Learning algorithm can be used with different types of function approximation (tabular and neural network), eligibility traces (Singh & Sutton (1996) <doi:10.1007/BF00114726>) and experience replay (Mnih et al. (2013) <arXiv:1312.5602>).

Getting started

Package details

Maintainer
LicenseMIT + file LICENSE
Version0.1.0
URL http://markusdumke.github.io/reinforcelearn
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("devtools")
library(devtools)
install_github("markdumke/reinforceR")
markdumke/reinforceR documentation built on Jan. 4, 2018, 4:52 a.m.