Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes.
Tomás BrázdilVáclav BrozekKrishnendu ChatterjeeVojtech ForejtAntonín KuceraPublished in: LICS (2011)
Keyphrases
- markov decision processes
- reinforcement learning
- finite state
- optimal policy
- transition matrices
- finite horizon
- state space
- dynamic programming
- policy iteration
- reachability analysis
- decision theoretic planning
- partially observable
- average reward
- risk sensitive
- decision processes
- action space
- reinforcement learning algorithms
- factored mdps
- action sets
- planning under uncertainty
- data mining
- stochastic games
- multi objective