Towards Return Parity in Markov Decision Processes.
Jianfeng ChiJian ShenXinyi DaiWeinan ZhangYuan TianHan ZhaoPublished in: AISTATS (2022)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- policy iteration
- dynamic programming
- transition matrices
- reinforcement learning
- markov decision process
- decision theoretic planning
- model based reinforcement learning
- reinforcement learning algorithms
- partially observable
- decision processes
- reachability analysis
- reward function
- infinite horizon
- action sets
- average cost
- risk sensitive
- factored mdps
- continuous state spaces
- discounted reward