paper-with-me

Papers

Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot

2023-07-31 · Tao Huang, Kai Chen, Wang Wei, Jianan Li, Yonghao Long, Qi Dou

Reinforcement learning is still struggling with solving long-horizon surgical robot tasks which involve multiple steps over an extended duration of time due to the policy exploration challenge. Recent methods try to tackle this problem by skill chaining, in which the long-horizon task is decomposed into multiple subtasks for easing the exploration burden and subtask policies are temporally connected to complete the whole long-horizon task. However, smoothly connecting all subtask policies is difficult for surgical robot scenarios. Not all states are equally suitable for connecting two adjacent subtasks. An undesired terminate state of the previous subtask would make the current subtask policy unstable and result in a failed execution. In this work, we introduce value-informed skill chaining (ViSkill), a novel reinforcement learning framework for long-horizon surgical robot tasks. The core idea is to distinguish which terminal state is suitable for starting all the following subtask policies. To achieve this target, we introduce a state value function that estimates the expected success probability of the entire task given a state. Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task. We demonstrate the effectiveness of our method on three complex surgical robot tasks from SurRoL, a comprehensive surgical simulation platform, achieving high task success rates and execution efficiency. Code is available at $\href{https://github.com/med-air/ViSkill}{\text{https://github.com/med-air/ViSkill}}$.

📄 PDF Abstract BibTeX arXiv:2307.16503

Code (1)

med-air/viskill 공식 구현 pytorch

Tasks

reinforcement-learning

Similar Papers 제목 키워드 기반

Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization

2021-11-15 · Youngwoon Lee, Joseph J. Lim, Anima Anandkumar, Yuke Zhu

Skill chaining is a promising approach for synthesizing complex behaviors by sequentially combining previously learned skills. Yet, a naive composition of skills fails when a policy encounters a starting state never seen…

Reinforcement Learning (RL)Robot Manipulation

Option Discovery using Deep Skill Chaining

2020-05-01 · ICLR 2020 1 · Akhil Bagaria, George Konidaris

Autonomously discovering temporally extended actions, or skills, is a longstanding goal of hierarchical reinforcement learning. We propose a new algorithm that combines skill chaining with deep neural networks to autonom…

continuous-controlContinuous ControlHierarchical Reinforcement Learningreinforcement-learning+2

Latent Plans for Task-Agnostic Offline Reinforcement Learning

2022-09-19 · Erick Rosete-Beas, Oier Mees, Gabriel Kalweit, Joschka Boedecker 외

Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still impose a major challenge in offline robot control. While a number of prior methods aimed to address this setting with variants …

Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation

2026-06-24 · Runyi Yu, Xiaoyi Lin, Ji Ma, Yinhuai Wang 외 arxiv

Learning long-horizon humanoid loco-manipulation poses a dual challenge: it requires not only the robust execution of meta-skills but also their seamless, closed-loop chaining equipped with autonomous recovery. Existing …

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

2025-09-26 · Pei Xu, Zhen Wu, Ruocheng Wang, Vishnu Sarukkai 외 arxiv

Learning a control policy for a multi-phase, long-horizon task, such as basketball maneuvers, remains challenging for reinforcement learning approaches due to the need for seamless policy composition and transitions betw…

Reinforcement Learning