Games and Markov Decision Processes with Mean-Payoff Parity and Energy Parity Objectives.
Krishnendu ChatterjeeLaurent DoyenPublished in: MEMICS (2011)
Keyphrases
- markov decision processes
- action sets
- stochastic games
- game theory
- state space
- reinforcement learning
- finite state
- optimal policy
- transition matrices
- dynamic programming
- infinite horizon
- reachability analysis
- finite horizon
- decision theoretic planning
- decision processes
- policy iteration
- nash equilibrium
- planning under uncertainty
- state and action spaces
- factored mdps
- reinforcement learning algorithms
- markov decision process
- risk sensitive
- repeated games
- action space
- average cost
- model based reinforcement learning
- average reward
- semi markov decision processes
- partially observable
- reward function
- multiple objectives
- stochastic shortest path
- real time dynamic programming
- long run
- multi objective