On the Heterogeneity of Independent Learning Dynamics in Zero-sum Stochastic Games.
Muhammed O. SayinK. Alperen CetinerPublished in: L4DC (2022)
Keyphrases
- genetic algorithm
- stochastic games
- learning automata
- nash equilibria
- multiagent reinforcement learning
- repeated games
- games with incomplete information
- markov decision processes
- nash equilibrium
- multi agent
- learning process
- learning agent
- game theory
- learning tasks
- incomplete information
- resource allocation
- average reward
- imperfect information
- search algorithm
- learning algorithm
- neural network