7 citations · 8 across the 14 of their papers we have counts for
11 papers · 1 filter
On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models
Yang Yu
World-action models predict a future outcome and then infer an associated action. Although this factorization can improve representation learning and data efficiency, it is unclear…
How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
Yang Yu, Shiyuan Zhang, Yifei Sheng +2
World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models, latent imagination models, fut…
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
Ke Zhao, Zixiang Di, Hong Qian +9
Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented…
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…
Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization
Lanqing Li, Shentong Mo, Yang Yu +1
Protein language models (PLMs) have emerged as powerful tools for controllable biomolecular design, yet their post-training adaptation typically relies on costly wet-lab validation…
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…
VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents
Pengsen Liu, Maosen Zeng, Nan Tang +4
Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typical…
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…
Policy Optimization in RLHF: The Impact of Out-of-preference Data
Ziniu Li, Tian Xu, Yang Yu
Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model…
Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning
Fan-Ming Luo, Tian Xu, Xingchen Cao +1
Learning a precise dynamics model can be crucial for offline reinforcement learning, which, unfortunately, has been found to be quite challenging. Dynamics models that are learned…
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang +4
Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO…