北京通用人工智能研究院BIGAI

科研成果

Constrained Update Projection Approach to Safe Policy Optimization

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Online Tensor Low-Rank Representation for Streaming Data Clustering

MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control

TarGF: Learning Target Gradient Field for Object Rearrangement

EgoTaskQA: Understanding Human Tasks in Egocentric Videos