Hidden Parameter Markov Decision Processes: An Emerging Paradigm for Modeling Families of Related Tasks.
George Dimitri KonidarisFinale Doshi-VelezPublished in: AAAI Fall Symposia (2014)
Keyphrases
- markov decision processes
- state space
- optimal policy
- reinforcement learning
- finite state
- policy iteration
- transition matrices
- dynamic programming
- reachability analysis
- state and action spaces
- decision theoretic planning
- planning under uncertainty
- average reward
- decision processes
- reinforcement learning algorithms
- partially observable
- action space
- data mining
- factored mdps
- average cost
- infinite horizon
- markov decision process
- learning rate
- transfer learning
- finite horizon
- markov decision problems
- reward function
- linear programming
- model based reinforcement learning