Reinforcement Learning Algorithms for Episodic MDPs With Finite SA-Spaces
Julia Jupyter Notebook
Switch branches/tags
Nothing to show
Clone or download
Latest commit bf36790 May 9, 2017

README.md

FiniteEpisodicRL.jl

Reinforcement Learning Algorithms for Episodic MDPs With Finite SA-Spaces Source code for experiments in

UBEV - A More Practical Algorithm for Episodic RL with Near-Optimal PAC and Regret Guarantees
Christoph Dann, Tor Lattimore, Emma Brunskill
https://arxiv.org/abs/1703.07710

For Python implementations of some of the algorithms see https://github.com/iosband/TabulaRL/