Non-Cooperative Rational Synthesis Problem on Stochastic Games for Positional Strategies.
So KoideYoshiaki TakataHiroyuki SekiPublished in: IEICE Trans. Inf. Syst. (2024)
Keyphrases
- stochastic games
- cooperative
- multiagent reinforcement learning
- repeated games
- multi agent reinforcement learning
- nash equilibria
- multi agent
- game theory
- markov decision processes
- nash equilibrium
- single agent
- decision making
- reinforcement learning algorithms
- multi agent systems
- average reward
- learning automata
- neural network
- infinite horizon