145 citations · 155 across the 18 of their papers we have counts for
20 papers
System Design for Maintaining Internal State Consistency in Long-Horizon Robotic Tabletop Games
Guangyu Zhao, Ceyao Zhang, Chengdong Ma +16
Long-horizon tabletop games pose a distinct systems challenge for robotics: small perceptual or execution errors can invalidate accumulated task state, propagate across decision-ma…
Accelerating Robotic Reinforcement Learning with Agent Guidance
Haojun Chen, Zili Zou, Chengdong Ma +4
Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application i…
Finding Kissing Numbers with Game-theoretic Reinforcement Learning
Chengdong Ma, Théo Tao Zhaowei, Pengyu Li +7
Since Isaac Newton first studied the Kissing Number Problem in 1694, determining the maximal number of non-overlapping spheres around a central sphere has remained a defining chall…
World Models Should Prioritize the Unification of Physical and Social Dynamics
Xiaoyuan Zhang, Chengdong Ma, Yizhe Huang +5
World models, which explicitly learn environmental dynamics to lay the foundation for planning, reasoning, and decision-making, are rapidly advancing in predicting both physical dy…
Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li +13
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. Howev…
Social World Model-Augmented Mechanism Design Policy Learning
Xiaoyuan Zhang, Yizhe Huang, Chengdong Ma +6
Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with model…
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Zheng Yuwei +12
Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose failure causes worst-case system performance degradations.…
Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
Yan Yu, Yaodong Yang, Zhengbo Lu +3
Causal inference is crucial for humans to explore the world, which can be modeled to enable an agent to efficiently explore the environment in reinforcement learning. Existing rese…
Falcon: Fast Visuomotor Policies via Partial Denoising
Haojun Chen, Minghao Liu, Chengdong Ma +8
Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for ac…
Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
Zhaowei Zhang, Fengshuo Bai, Qizhi Chen +5
How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, chang…
Conflux-PSRO: Effectively Leveraging Collective Advantages in Policy Space Response Oracles
Yucong Huang, Jiesong Lian, Mingzhi Wang +2
Policy Space Response Oracle (PSRO) with policy population construction has been demonstrated as an effective method for approximating Nash Equilibrium (NE) in zero-sum games. Exis…
Sample-Efficient Regret-Minimizing Double Oracle in Extensive-Form Games
Xiaohang Tang, Chiyuan Wang, Chengdong Ma +3
Extensive-Form Game (EFG) represents a fundamental model for analyzing sequential interactions among multiple agents and the primary challenge to solve it lies in mitigating sample…
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
Mingzhi Wang, Chengdong Ma, Qizhi Chen +7
Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF),…
Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning
Wenzhe Fan, Zishun Yu, Chengdong Ma +3
In multi-agent reinforcement learning, a commonly considered paradigm is centralized training with decentralized execution. However, in this framework, decentralized execution rest…
A Survey on Self-play Methods in Reinforcement Learning
Ruize Zhang, Zelai Xu, Chengdong Ma +8
Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has show…
Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oracles
Jiesong Lian, Yucong Huang, Chengdong Ma +4
For solving zero-sum games involving non-transitivity, a useful approach is to maintain a policy population to approximate the Nash Equilibrium (NE). Previous studies have shown th…
Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems
Zhaowei Zhang, Fengshuo Bai, Mingzhi Wang +3
The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides h…
Panacea: Pareto Alignment via Preference Adaptation for LLMs
Yifan Zhong, Chengdong Ma, Xiaoyuan Zhang +5
Current methods for large language model alignment typically use scalar human preference labels. However, this convention tends to oversimplify the multi-dimensional and heterogene…
Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games
Chengdong Ma, Ziran Yang, Hai Ci +4
The primary challenge in deploying Large Language Model (LLM) is ensuring its harmlessness. Red team can identify vulnerabilities by attacking LLM to attain safety. However, curren…
Game-Theoretic Multiagent Reinforcement Learning
Yaodong Yang, Chengdong Ma, Zihan Ding +4
Tremendous advances have been made in multiagent reinforcement learning (MARL). MARL corresponds to the learning problem in a multiagent system in which multiple agents learn simul…