Hedging Bets in Markov Decision Processes.
Rajeev AlurMarco FaellaSampath KannanNimit SinghaniaPublished in: CSL (2016)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- dynamic programming
- optimal policy
- transition matrices
- average cost
- reachability analysis
- policy iteration
- decision theoretic planning
- model based reinforcement learning
- partially observable
- factored mdps
- reinforcement learning algorithms
- state and action spaces
- planning under uncertainty
- infinite horizon
- risk sensitive
- average reward
- action space
- finite horizon
- decision processes
- action sets
- markov decision process
- dynamical systems
- data mining