Decentralized Q-Learning for Stochastic Teams and Games.
Gürdal ArslanSerdar YükselPublished in: IEEE Trans. Autom. Control. (2017)
Keyphrases
- multi agent
- cooperative
- stochastic approximation
- game theory
- multiagent learning
- learning agents
- reinforcement learning
- game theoretic
- multi agent reinforcement learning
- peer to peer
- computer games
- function approximation
- team members
- nash equilibria
- game playing
- single agent
- learning automata
- learning algorithm
- nash equilibrium
- video games
- multi agent systems
- temporal difference learning
- distributed systems
- stochastic games
- team formation
- multiple agents
- game design
- imperfect information
- game development
- online game
- educational games
- monte carlo
- multi robot systems
- decision making