Successively Pruned Q-Learning: Using Self Q-function to Reduce the Overestimation.

Zhaolin Xue Lihua Zhang Zhiyan Dong

Published in: AAMAS (2024)

Keyphrases

reinforcement learning
cooperative
multi agent
state space
function approximation
information systems
dynamic programming
learning algorithm
knowledge base
website
multi agent systems
hierarchical structure
learning rate
piecewise linear
reinforcement learning algorithms
multi agent reinforcement learning