Markov Decision Processes and Stochastic Games with Total Effective Payoff.
Endre BorosKhaled M. ElbassioniVladimir GurvichKazuhisa MakinoPublished in: STACS (2015)
Keyphrases
- markov decision processes
- stochastic games
- average reward
- repeated games
- optimal policy
- finite state
- state space
- nash equilibrium
- reinforcement learning
- reinforcement learning algorithms
- policy iteration
- dynamic programming
- nash equilibria
- multiagent reinforcement learning
- markov decision process
- infinite horizon
- game theory
- average cost
- finite horizon
- partially observable
- model free
- computational complexity
- optimal solution