Fast Peer Adaptation with Context-aware Exploration
Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院）；Center on Frontiers of Computing Studies, School of Computer Science, Peking University（北京大学计算机学院计算前沿研究中心）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Inst. for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Nat’l Key Laboratory of General Artificial Intelligence, BIGAI&PKU（通用人工智能国家重点实验室（北京通用人工智能研究院与北京大学联合））；Nat’l Eng. Research Center of Visual Technology, Peking University（北京大学视觉技术国家工程研究中心）
Long Ma, Yuanfei Wang, Fangwei Zhong, Song-Chun Zhu, Yizhou Wang
Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation. However, exploring the strategies of unknown peers is difficult, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods.
Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Multi-Agent Navigation
Tsinghua University（清华大学）；Stevens Institute of Technology（史蒂文斯理工学院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Texas A&M University（德克萨斯A&M大学）
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering
State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD与CG国家重点实验室）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；School of Software Technology, Zhejiang University（浙江大学软件技术学院）
Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations
Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Centre for Cognitive Science（认知科学中心）
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Department of Computer Science & Technology, Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University（计算机科学与技术系、人工智能研究院、BNRist中心、清华-博世联合机器学习中心、THBI实验室、清华大学）
From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?
School of Electronic and Information Engineering, Foshan University（佛山大学电子与信息工程学院）；School of Software & Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University（山东大学软件学院及山东大学-新加坡国立大学人工智能联合研究中心）；Skywork AI（天工AI）
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of Michigan（密歇根大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Northeastern University（东北大学）；Michigan State University（密歇根州立大学）
