Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes
Tomás BrázdilVáclav BrozekKrishnendu ChatterjeeVojtech ForejtAntonín KuceraPublished in: Log. Methods Comput. Sci. (2014)
Keyphrases
- markov decision processes
- state space
- optimal policy
- reinforcement learning
- finite state
- transition matrices
- decision theoretic planning
- policy iteration
- infinite horizon
- factored mdps
- dynamic programming
- state and action spaces
- reachability analysis
- reinforcement learning algorithms
- action sets
- risk sensitive
- decision processes
- finite horizon
- average cost
- partially observable
- planning under uncertainty
- action space
- model based reinforcement learning
- heuristic search
- game theory
- markov decision process