epsilon-Equilibria for Stochastic Games with Uncountable State Space and Unbounded Costs.
Andrzej S. NowakEitan AltmanPublished in: SIAM J. Control. Optim. (2002)
Keyphrases
- stochastic games
- state space
- nash equilibria
- games with incomplete information
- markov decision processes
- reinforcement learning algorithms
- repeated games
- nash equilibrium
- incomplete information
- average cost
- optimal policy
- reinforcement learning
- game theory
- learning agent
- average reward
- game theoretic
- multiagent reinforcement learning
- heuristic search
- markov chain
- infinite horizon
- learning automata
- long run
- state variables
- particle filter
- complexity analysis
- planning problems
- dynamic programming
- partially observable
- model free
- policy iteration
- action space
- dynamical systems
- search space
- initial state
- fixed point