Distributionally Robust Counterpart in Markov Decision Processes.
Pengqian YuHuan XuPublished in: CoRR (2015)
Keyphrases
- markov decision processes
- robust optimization
- optimal policy
- mathematical programming
- stochastic programming
- reinforcement learning
- finite state
- state space
- policy iteration
- transition matrices
- dynamic programming
- factored mdps
- average reward
- planning under uncertainty
- markov decision process
- reachability analysis
- finite horizon
- partially observable
- infinite horizon
- model based reinforcement learning
- action space
- multistage
- average cost
- reward function
- lot sizing
- decision theoretic planning
- semidefinite programming
- action sets
- decision theory
- state and action spaces
- data mining