Learning Representation and Control in Markov Decision Processes: New Frontiers.
Sridhar MahadevanPublished in: Found. Trends Mach. Learn. (2009)
Keyphrases
- markov decision processes
- reinforcement learning
- decision theoretic planning
- learning algorithm
- optimal policy
- stochastic games
- dynamic programming
- partially observable
- state space
- model based reinforcement learning
- finite state
- optimal control
- infinite horizon
- learning tasks
- control problems
- markov decision process
- decision problems
- linear programming
- machine learning