Towards Return Parity in Markov Decision Processes.
Jianfeng ChiJian ShenXinyi DaiWeinan ZhangYuan TianHan ZhaoPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- state space
- policy iteration
- dynamic programming
- finite state
- decision theoretic planning
- planning under uncertainty
- finite horizon
- factored mdps
- reinforcement learning algorithms
- transition matrices
- reachability analysis
- infinite horizon
- decision processes
- markov decision process
- risk sensitive
- average reward
- partially observable
- action space
- model based reinforcement learning
- state and action spaces
- action sets
- reward function
- model free
- multistage
- real time dynamic programming