Adaptive Planning for Markov Decision Processes with Uncertain Transition Models via Incremental Feature Dependency Discovery.
N. Kemal UreAlborz GeramifardGirish ChowdharyJonathan P. HowPublished in: ECML/PKDD (2) (2012)
Keyphrases
- markov decision processes
- transition matrices
- planning under uncertainty
- finite state
- reinforcement learning
- optimal policy
- decision theoretic planning
- partially observable
- finite horizon
- dynamic programming
- state space
- macro actions
- reinforcement learning algorithms
- probabilistic planning
- average cost
- reachability analysis
- decision processes
- infinite horizon
- markov models
- average reward
- policy iteration
- data mining
- factored mdps
- heuristic search
- model based reinforcement learning
- machine learning