Model-Free Reinforcement Learning R package ReinforcementLearning version 1.0.5 Performs model-free reinforcement learning in R. This implementation enables the learning of an optimal policy based on sample sequences consisting of states, actions and rewards. In addition, it supplies multiple predefined reinforcement learning algorithms, such as experience replay. Methodological details can be found in Sutton and Barto (1998) <ISBN:0262039249>. Software Depends: R (>= 3.2.0) Imports: ggplot2, hash (>= 2.0), data.table Suggests: testthat, knitr, rmarkdown Nicolas Proellochs <nicolas.proellochs@wi.jlug.de> Comprehensive R Archive Network (CRAN) Nicolas Proellochs [aut, cre], Stefan Feuerriegel [aut] MIT + file LICENSE (https://CRAN.R-project.org/package=ReinforcementLearning/LICENSE) 2020-03-02 application/tgz https://CRAN.R-project.org/package=ReinforcementLearning doi:10.32614/CRAN.package.ReinforcementLearning