26 citations · 63 across the 24 of their papers we have counts for
7 papers · 1 filter
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Tian Xu, Zexuan Chen, Zhilong Zhang +4
Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical w…
Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning
Zihao Wang, Shijie Peng, Kerui Wu +6
Humans exhibit remarkable motor agility, enabling a wide range of dynamic skills such as running and jumping, which highlights the great potential of humanoid robots for athletic l…
How Can Reinforcement Learning Achieve Expert-level Placement?
Ruo-Tong Chen, Ke Xue, Chengrui Gao +7
Chip placement is a critical step in physical design. While reinforcement learning (RL)-based methods have recently emerged, their training primarily focuses on wirelength optimiza…
Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
Tian Xu, Zhilong Zhang, Zexuan Chen +3
Adversarial imitation learning (AIL), a prominent approach in imitation learning, has achieved significant practical success powered by neural network approximation. However, exist…
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu +8
Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant R…
Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism
Tian Xu, Chenyang Wang, Xiaochen Zhai +3
Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors inherent to behavioral cloning (BC), yet its adversarial optimization frequent…
Eval-Actions: Fine-Grained Execution Quality Evaluation for Robotic Manipulation
Mengyuan Liu, Juyi Sheng, Peiming Li +4
Although Vision--Action (VA) and Vision--Language--Action (VLA) policies have advanced robotic manipulation, their evaluation remains dominated by binary success rates, which obscu…