Cross Domain Policy Transfer with Effect Cycle-Consistency

no code implementations • 4 Mar 2024 • Ruiqi Zhu, Tianhong Dai, Oya Celiktutan

Unlike prior methods that rely on paired data, we propose a novel approach for learning the mapping functions between state and action spaces across domains using unpaired data.

Learning to Solve Tasks with Exploring Prior Behaviours

1 code implementation • 6 Jul 2023 • Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang, Oya Celiktutan

Our method can endow agents with the ability to explore and acquire the required prior behaviours and then connect to the task-specific behaviours in the demonstration to solve sparse-reward tasks without requiring additional demonstration of the prior behaviours.

Deep Reinforcement Learning Based Semi-Autonomous Control for Robotic Surgery

no code implementations • 11 Apr 2022 • Ruiqi Zhu, Dandan Zhang, Benny Lo

In recent decades, the tremendous benefits surgical robots have brought to surgeons and patients have been witnessed.

reinforcement-learning Reinforcement Learning (RL)