Hidden-Mode Markov Decision Processes for Nonstationary Sequential Decision Making.
Samuel P. M. ChoiDit-Yan YeungNevin Lianwen ZhangPublished in: Sequence Learning (2001)
Keyphrases
- markov decision processes
- non stationary
- sequential decision making
- reinforcement learning
- decision problems
- optimal policy
- reinforcement learning algorithms
- state space
- policy iteration
- dynamic programming
- finite state
- finite horizon
- influence diagrams
- transition matrices
- infinite horizon
- random fields
- decision theoretic planning
- average reward
- machine learning
- optimal control
- markov decision process
- learning algorithm
- function approximation
- temporal difference
- reward function
- expected utility
- supervised learning
- multi agent
- model free
- action selection
- decision making
- long run