6 papers
Generalizable Hierarchical Skill Learning via Object-Centric Representation
Haibo Zhao, Yu Qi, Boce Hu +9
We present Generalizable Hierarchical Skill Learning (GSL), a novel framework for hierarchical policy learning that significantly improves policy generalization and sample efficien…
Recursive Deep Inverse Reinforcement Learning
Paul Ghanem, Owen Howell, Michael Potter +4
Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy…
Clebsch-Gordan Transformer: Fast and Global Equivariant Attention
Owen Lewis Howell, Linfeng Zhao, Xupeng Zhu +6
The global attention mechanism is one of the keys to the success of transformer architecture, but it incurs quadratic computational costs in relation to the number of tokens. On th…
Hierarchical Equivariant Policy via Frame Transfer
Haibo Zhao, Dian Wang, Yizhe Zhu +6
Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and…
NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models
Zhuoran Qiao, Feizhi Ding, Thomas Dresselhaus +10
Structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have…
Equivariant Action Sampling for Reinforcement Learning and Planning
Linfeng Zhao, Owen Howell, Xupeng Zhu +4
Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent pro…