Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL.

Xiaoyu Chen Jiachen Hu Lihong Li Liwei Wang

Published in: ICLR (2021)

Keyphrases

reinforcement learning
factored mdps
markov decision processes
state space
approximate dynamic programming
optimal policy
policy iteration
function approximation
multi agent
model free
reinforcement learning algorithms
machine learning
cost function
supervised learning
temporal difference