On the Role of Discount Factor in Offline Reinforcement Learning.

Hao Hu Yiqin Yang Qianchuan Zhao Chongjie Zhang

Published in: CoRR (2022)

Keyphrases

reinforcement learning
optimal policy
discount factor
markov decision processes
markov decision problems
state space
function approximation
long run
learning algorithm
multi agent
dynamic programming
linear programming
steady state
decision problems
markov decision process
average reward