The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics.

Aamal Abbas Hussain Francesco Belardinelli Dario Paccagnan

Published in: ICML (2023)

Keyphrases

multi agent
reinforcement learning
cooperative
stochastic approximation
multi agent simulation
single agent
exploration strategy

initial conditions
action selection
agent based simulations
multi agent systems
intelligent agents
multiagent systems
dynamical systems

autonomous agents
heterogeneous agents
coalition formation
learning algorithm
neural network
convergence proof
multi agent reinforcement learning

iterative algorithms
learning rate
convergence rate
multiagent learning
temporal difference learning
agent based models
genetic algorithm