Optimizing the Expected Mean Payoff in Energy Markov Decision Processes.
Tomás BrázdilAntonín KuceraPetr NovotnýPublished in: ATVA (2016)
Keyphrases
- markov decision processes
- total reward
- optimal policy
- finite state
- reinforcement learning
- policy iteration
- state space
- transition matrices
- reinforcement learning algorithms
- risk sensitive
- infinite horizon
- planning under uncertainty
- stationary policies
- decision theoretic planning
- reachability analysis
- average reward
- model based reinforcement learning
- action space
- factored mdps
- dynamic programming
- average cost
- partially observable
- decision processes
- action sets
- game theory
- stochastic games
- semi markov decision processes
- reward function