6 papers
PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems
Yingfan Deng, Anhao Zhou, Yuan Yuan +3
Multi-Agent Systems have recently emerged as a promising paradigm for collaborative reasoning and solving complex tasks. However, the design of collaborative learning algorithms in…
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Yan Li, Xiao Zhang, Mingyi Li +7
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve…
Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation
Yanwei Zheng, Changrui Li, Chuanlin Lan +5
Zero-shot object navigation (ZSON) addresses situation where an agent navigates to an unseen object that does not present in the training set. Previous works mainly train agent usi…
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
Mengtong Gao, Yifei Zou, Zuyuan Zhang +2
The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates…
John's blow up examples and scattering solutions for semi-linear wave equations
Louie Bernhardt, Volker Schlue, Dongxiao Yu
In light of recent work of the third author, we revisit a classic example given by Fritz John of a semi-linear wave equation which exhibits finite in time blow up for all compactly…
ConcaveQ: Non-Monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning
Huiqun Li, Hanhan Zhou, Yifei Zou +2
Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-…