Percentile Optimization for Markov Decision Processes with Parameter Uncertainty.
Erick DelageShie MannorPublished in: Oper. Res. (2010)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- dynamic programming
- policy iteration
- reachability analysis
- transition matrices
- reinforcement learning
- planning under uncertainty
- reinforcement learning algorithms
- average reward
- finite horizon
- average cost
- factored mdps
- decision theoretic planning
- robust optimization
- infinite horizon
- semi markov decision processes
- reward function
- partially observable
- risk sensitive
- discounted reward
- stochastic shortest path
- action sets
- decision processes
- markov decision process
- monte carlo
- model based reinforcement learning
- markov chain
- data mining