Reinforcement Learning

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

GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning …

Hanjing Wang, Man-Kit Sit, Congjie He, Ying Wen, Weinan Zhang, Jun Wang, Yaodong Yang, Luo Mai

A Deep Reinforcement Learning-driven Vine Copula Method for Correlation Structure Analysis of Mortgage

Controlling risk is the key to playing a core role in financial services and effectively serving the high-quality development of the …

Qinghao Wang, Yanling PENG, Yijie Peng, Yaodong Yang

Learning to Shape Rewards using a Game of Two Partners

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. …

David Mguni, Taher Jafferjee, Jianhong Wang, Nicolas Perez Nieves, Tianpei Yang, Matthew Taylor, Wenbin Song, Feifei Tong, Hui Chen, Jiangcheng Zhu, Jun Wang, Yaodong Yang

Quality-Similar Diversity via Population Based Reinforcement Learning

Diversity is a growing research topic in Reinforcement Learning (RL). Previous research on diversity has mainly focused on promoting …

Shuang Wu, Jian Yao, Haobo Fu, Ye Tian, Chao Qian, Yaodong Yang, QIANG FU, Yang Wei

Solving Inventory Management Problems through Deep Reinforcement Learning

Inventory management (e.g. lost sales) is a central problem in supply chain management. Lost sales inventory systems with lead times …

Qinghao Wang, Yijie Peng, Yaodong Yang

MSRL: Distributed Reinforcement Learning with Dataflow Fragments

Reinforcement learning (RL) trains many agents, which is resource-intensive and must scale to large GPU clusters. Different RL training …

Huanzhou Zhu, Bo Zhao, Gang Chen, Weifeng Chen, Yijie Chen, Liang Shi, Yaodong Yang, Peter Pietzuch, Lei Chen

Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning

Setting up a well-designed reward function has been challenging for many reinforcement learning applications. Preference-based …

Runze Liu, Fengshuo Bai, Yali Du, Yaodong Yang

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Achieving human-level dexterity is an important open problem in robotics. However, tasks of dexterous hand manipulation even at the …

Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang

End-to-End Affordance Learning for Robotic Manipulation

Learning to manipulate 3D objects in an interactive environment has been a challenging problem in Reinforcement Learning (RL). In …

Yiran Geng, Boshi An, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong