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