ReinforcementLearning: Model-Free Reinforcement Learning

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>.

Version: 1.0.5
Depends: R (≥ 3.2.0)
Imports: ggplot2, hash (≥ 2.0), data.table
Suggests: testthat, knitr, rmarkdown
Published: 2020-03-02
DOI: 10.32614/CRAN.package.ReinforcementLearning
Author: Nicolas Proellochs [aut, cre], Stefan Feuerriegel [aut]
Maintainer: Nicolas Proellochs <nicolas.proellochs at wi.jlug.de>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README NEWS
CRAN checks: ReinforcementLearning results

Documentation:

Reference manual: ReinforcementLearning.pdf
Vignettes: Reinforcement Learning in R

Downloads:

Package source: ReinforcementLearning_1.0.5.tar.gz
Windows binaries: r-devel: ReinforcementLearning_1.0.5.zip, r-release: ReinforcementLearning_1.0.5.zip, r-oldrel: ReinforcementLearning_1.0.5.zip
macOS binaries: r-release (arm64): ReinforcementLearning_1.0.5.tgz, r-oldrel (arm64): ReinforcementLearning_1.0.5.tgz, r-release (x86_64): ReinforcementLearning_1.0.5.tgz, r-oldrel (x86_64): ReinforcementLearning_1.0.5.tgz
Old sources: ReinforcementLearning archive

Reverse dependencies:

Reverse imports: lazytrade

Linking:

Please use the canonical form https://CRAN.R-project.org/package=ReinforcementLearning to link to this page.