Solving Hidden-Mode Markov Decision Problems.
Samuel Ping-Man ChoiNevin Lianwen ZhangDit-Yan YeungPublished in: AISTATS (2001)
Keyphrases
- markov decision problems
- linear programming
- partially observable
- state space
- reinforcement learning
- decision theoretic
- decision processes
- optimal policy
- dynamic programming
- expected utility
- utility function
- markov decision processes
- transition probabilities
- policy iteration
- average cost
- decision problems
- queueing networks
- orders of magnitude
- function approximators
- markov chain
- supervised learning
- stochastic shortest path