Decentralized Q-Learning for Stochastic Dynamic Games.
Gürdal ArslanSerdar YükselPublished in: CoRR (2015)
Keyphrases
- stochastic dynamic
- multi agent
- cooperative
- reinforcement learning
- multiagent learning
- function approximation
- game theory
- computer games
- video games
- state space
- nash equilibrium
- game playing
- game design
- learning rate
- nash equilibria
- distributed systems
- distributed agents
- learning algorithm
- optimal policy
- peer to peer
- neural network
- model free
- action selection
- learning agents
- human computation
- coalitional games
- stochastic games
- coordination mechanism
- multi agent systems
- dynamic programming
- perfect information
- temporal difference learning
- educational games
- single agent
- game theoretic
- multiagent systems
- game play