B2MAPO: A Batch-by-Batch Multi-Agent Policy Optimization to Balance Performance and Efficiency.

Wenjing Zhang Wei Zhang Wenqing Hu Yifan Wang

Published in: CoRR (2024)

Keyphrases

multi agent
batch mode
optimization algorithm
optimization problems
batch processing
neural network
multi agent systems
computational efficiency
global optimization
quality prediction
computational complexity
multi objective
optimal policy
optimization method