Modelling the dynamics of multiagent Q-learning with ε-greedy exploration.
Eduardo Rodrigues GomesRyszard KowalczykPublished in: AAMAS (2) (2009)
Keyphrases
- multi agent
- cooperative
- exploration strategy
- agent based models
- greedy algorithm
- agent based simulations
- reinforcement learning
- action selection
- locally optimal
- multi agent systems
- single agent
- multiagent systems
- dynamic model
- intelligent agents
- multiagent learning
- function approximation
- dynamical systems
- dynamic programming
- search algorithm
- learning algorithm
- greedy algorithms
- multiple agents
- feature selection
- autonomous agents
- learning agents
- multi agent learning
- multi agent reinforcement learning
- decision trees
- multiagent reinforcement learning