1

ProgressGym: Alignment with a Millennium of Moral Progress

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such …

Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang

Efficient adaptation in mixed-motive environments via hierarchical opponent modeling and planning

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in …

Yizhe Huang, Anji Liu, Fanqi Kong, Yaodong Yang, Song-Chun Zhu, Xue Feng

Anyskill: Learning open-vocabulary physical skill for interactive agents

Traditional approaches in physics-based motion generation centered around imitation learning and reward shaping often struggle to adapt …

Jieming Cui, Tengyu Liu, Nian Liu, Yaodong Yang, Yixin Zhu, Siyuan Huang

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the …

Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Grasp multiple objects with one hand

The intricate kinematics of the human hand enable simultaneous grasping and manipulation of multiple objects, essential for tasks, such …

Yuyang Li, Bo Liu, Yiran Geng, Puhao Li, Yaodong Yang, Yixin Zhu, Tengyu Liu, Siyuan Huang

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning

Centralized Training with Decentralized Execution (CTDE) has been proven to be an effective paradigm in cooperative multi-agent …

Sirui Chen, Zhaowei Zhang, Yaodong Yang, Yali Du

Maximum entropy heterogeneous-agent reinforcement learning

Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing …

Jiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu, QIANG FU, Xiaojun Chang, Yaodong Yang

BeaverTails: A Human-Preference Dataset for LLM Harmlessness Alignment

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). …

Jiaming Ji, Mickel Liu, Juntao Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, Yaodong Yang

Is Nash Equilibrium Approximator Learnable?

In this paper, we investigate the learnability of the function approximator that approximates Nash equilibrium (NE) for games generated …

Zhijian Duan, Wenhan Huang, Dinghuai Zhang, Yali Du, Jun Wang, Yaodong Yang, Xiaotie Deng

Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces …

Jiaming Ji, Borong Zhang, Jiayi Zhou, Xuehai Pan, Weidong Huang, Ruiyang Sun, Yiran Geng, Yifan Zhong, Juntao Dai, Yaodong Yang