Robust Average-Reward Markov Decision Processes.
Yue WangAlvaro VelasquezGeorge K. AtiaAshley Prater-BennetteShaofeng ZouPublished in: AAAI (2023)
Keyphrases
- markov decision processes
- average reward
- optimal policy
- policy iteration
- discounted reward
- semi markov decision processes
- state space
- stochastic games
- finite state
- reinforcement learning
- long run
- dynamic programming
- optimality criterion
- partially observable
- factored mdps
- state and action spaces
- reinforcement learning algorithms
- infinite horizon
- total reward
- planning under uncertainty
- model free
- markov decision process
- average cost
- decision theoretic planning
- partially observable markov decision processes
- machine learning
- hierarchical reinforcement learning
- real valued
- action space
- initial state