Classes of Multiagent Q-learning Dynamics with epsilon-greedy Exploration.
Michael WunderMichael L. LittmanMonica BabesPublished in: ICML (2010)
Keyphrases
- multi agent
- cooperative
- action selection
- reinforcement learning
- greedy algorithm
- single agent
- agent based simulations
- exploration strategy
- intelligent agents
- multiagent systems
- multiagent learning
- dynamic programming
- multi agent systems
- neural network
- locally optimal
- feature selection
- model free
- dynamic model
- active learning
- hill climbing
- complexity analysis
- search algorithm
- function approximation
- greedy heuristic
- agent communication
- dynamical systems
- simulated annealing