On the functional equations in undiscounted and sensitive discounted stochastic games.
Awi FedergruenPublished in: Z. Oper. Research (1980)
Keyphrases
- stochastic games
- markov decision processes
- average reward
- infinite horizon
- optimal policy
- nash equilibria
- long run
- reinforcement learning algorithms
- reinforcement learning
- multiagent reinforcement learning
- finite horizon
- state space
- dynamic programming
- finite state
- repeated games
- policy iteration
- nash equilibrium
- robust optimization
- markov chain
- model free
- learning automata
- multi agent
- dynamical systems
- mathematical model
- partially observable
- partially observable markov decision processes
- least squares