Building the Next Generation of Intelligent Machines

Model-free Neural Lyapunov Control for Safe Robot Navigation

Abstract— Co-learning a Twin Neural Lyapunov Function and Deep Reinforcement Learning control policy for locomotion tasks.

IROS'22

NeRP: Neural Rearrangement Planning for Unknown Objects

Abstract— NeRP is a learning-based approach for multi-step neural object rearrangement planning with never-before-seen objects in the real world.

RSS'21

Constrained Motion Planning Networks X

Abstract— CoMPNetX is a neural planning approach with a fast projection operator for solving constrained manipulation tasks.

TRO'21

Composing Task-Agnostic Policies via Deep Reinforcement Learning

Abstract— A deep reinforcement learning-based skill transfer and composition method for robot location tasks.

ICLR'20

Adversarial Imitation Via Variational Inverse Reinforcement Learning

Abstract— Empowerment-regularized Adversarial Inverse Reinforcement Learning to infer transferable near-optimal rewards functions.

ICLR'19