This work proposes Multi-Agent Flow-Pretrained Policy Optimization (MA-FPPO), which uses online fine-tuning to improve the cooperative behavior of models pretrained with flow matching through new interactions with the environment.
Guo-Wei Zou, Hao-Nan Chen, Hai-Tao Wang et al.· arXiv.org· 0 citations
G2MAF applies one globally normalized, projected critic gradient to guide and coordinate all agents'corrections while keeping the action both feasible and close to the frozen policy proposal.
Guo-Wei Zou, Hai-Tao Wang, Guo-Xin Wang et al.· arXiv.org· 0 citations
This work proposes Multi-Agent World-Action Model (MA-WAM), a test-time planning framework that enables a frozen multi-agent flow policy to evaluate futures of candidate joint actions and is the first test-time world-model planner for multi-agent flow policies.
Guo-Wei Zou, Hai-Tao Wang, Guo-Xin Wang et al.· 1 citation
CoFlow is proposed, which directly learns a joint averaged-velocity field for distillation-free one-step and few-step multi-agent trajectory generation and incorporates teammate trajectory information into each agent's prediction to support cooperation during generation.