Percentile optimization in uncertain Markov decision processes with application to efficient exploration.
Erick DelageShie MannorPublished in: ICML (2007)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- decision theoretic planning
- dynamic programming
- planning under uncertainty
- markov decision process
- average cost
- factored mdps
- decision making
- policy iteration
- transition matrices
- reinforcement learning algorithms
- heuristic search
- sufficient conditions
- multi agent
- machine learning
- action sets
- model based reinforcement learning
- data mining