Episodic task learning in Markov decision processes.
Yong LinFillia MakedonYurong XuPublished in: Artif. Intell. Rev. (2011)
Keyphrases
- markov decision processes
- reinforcement learning
- stochastic games
- state space
- model based reinforcement learning
- decision theoretic planning
- optimal policy
- partially observable
- dynamic programming
- finite state
- real time dynamic programming
- average cost
- policy iteration
- learning tasks
- learning algorithm
- infinite horizon
- function approximation
- finite horizon
- planning under uncertainty
- decision makers
- machine learning