Semi-infinitely Constrained Markov Decision Processes.
Liangyu ZhangYang PengWenhao YangZhihua ZhangPublished in: NeurIPS (2022)
Keyphrases
- markov decision processes
- transition matrices
- finite state
- state space
- optimal policy
- policy iteration
- reinforcement learning
- dynamic programming
- planning under uncertainty
- decision theoretic planning
- finite horizon
- finite number
- reachability analysis
- reinforcement learning algorithms
- infinite horizon
- average reward
- model based reinforcement learning
- factored mdps
- average cost
- markov decision process
- decision processes
- stochastic games
- semi markov decision processes
- monte carlo
- machine learning
- total reward
- risk sensitive
- supply chain
- sufficient conditions