Stochastic Games on a Product State Space.
János FleschGijs SchoenmakersKoos VriezePublished in: Math. Oper. Res. (2008)
Keyphrases
- stochastic games
- state space
- markov decision processes
- reinforcement learning algorithms
- learning agent
- reinforcement learning
- optimal policy
- average reward
- nash equilibria
- multiagent reinforcement learning
- repeated games
- markov chain
- heuristic search
- infinite horizon
- dynamic programming
- state variables
- dynamical systems
- learning automata
- decision problems
- planning problems
- multi agent
- finite state
- partially observable
- search space
- policy iteration
- model free
- function approximation
- markov decision process
- finite horizon
- particle filter
- nash equilibrium
- machine learning