Implements reinforcement learning environments and algorithms as described in Sutton & Barto (1998, ISBN:0262193981). The Q-Learning algorithm can be used with function approximation, eligibility traces (Singh & Sutton (1996) <doi:10.1007/BF00114726>) and experience replay (Mnih et al. (2013) <arXiv:1312.5602>).
https://anaconda.org/r_test/r-reinforcelearn/badges/version.svg
https://anaconda.org/r_test/r-reinforcelearn/badges/latest_release_date.svg
https://anaconda.org/r_test/r-reinforcelearn/badges/latest_release_relative_date.svg
https://anaconda.org/r_test/r-reinforcelearn/badges/platforms.svg
https://anaconda.org/r_test/r-reinforcelearn/badges/license.svg
https://anaconda.org/r_test/r-reinforcelearn/badges/downloads.svg