Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes.

Yi Tian Jian Qian Suvrit Sra

Published in: NeurIPS (2020)

Keyphrases

factored markov decision processes
reinforcement learning
dynamic programming
worst case
state space
multi agent
optimal control
markov decision problems
optimal solution
function approximation
learning algorithm
decision making
lower bound
optimal policy
temporal difference