Constraining an Unconstrained Multi-agent Policy with offline data.

 0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Cong Guan, Tao Jiang, Yi-Chen Li, Yang Yu, Lei Yuan, Zongzhang Zhang

Ngôn ngữ: eng

Ký hiệu phân loại: 005.116 +*Constraint programming

Thông tin xuất bản: United States : Neural networks : the official journal of the International Neural Network Society , 2025

Mô tả vật lý:

Bộ sưu tập: NCBI

ID: 199684

Real-world multi-agent decision-making systems often have to satisfy some constraints, such as harmfulness, economics, etc., spurring the emergence of Constrained Multi-Agent Reinforcement Learning (CMARL). Existing studies of CMARL mainly focus on training a constrained policy in an online manner, that is, not only maximizing cumulative rewards but also not violating constraints. However, in practice, online learning may be infeasible due to safety restrictions or a lack of high-fidelity simulators. Moreover, as the learned policy runs, new constraints, that are not taken into account during training, may occur. To deal with the above two issues, we propose a method called Constraining an UnconsTrained Multi-Agent Policy with offline data, dubbed CUTMAP, following the popular centralized training with decentralized execution paradigm. Specifically, we have formulated a scalable optimization objective within the framework of multi-agent maximum entropy reinforcement learning for CMARL. This approach is designed to estimate a decomposable Q-function by leveraging an unconstrained "prior policy"
Tạo bộ sưu tập với mã QR

THƯ VIỆN - TRƯỜNG ĐẠI HỌC CÔNG NGHỆ TP.HCM

ĐT: (028) 36225755 | Email: tt.thuvien@hutech.edu.vn

Copyright @2024 THƯ VIỆN HUTECH