An Adaptive Sampling Algorithm for Solving Markov Decision Processes.
Hyeong Soo ChangMichael C. FuJiaqiao HuSteven I. MarcusPublished in: Oper. Res. (2005)
Keyphrases
- markov decision processes
- sampling algorithm
- transition matrices
- semi markov decision processes
- random sampling
- optimal policy
- policy iteration
- finite state
- state space
- markov decision problems
- dynamic programming
- reinforcement learning
- average reward
- partially observable
- stochastic shortest path
- decision theoretic planning
- factored mdps
- markov decision process
- infinite horizon
- probability distribution
- markov chain monte carlo
- optical flow
- pairwise
- image segmentation