paper-with-me

Papers

Steering Generative Reinforcement Learning into Stable Robotic Controller

2026-06-15 · Yixuan Wang, Shutong Ding, Ke Hu, Tianxiang Gui, Jingya Wang, Ye Shi arxiv

Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by inducing rich stochastic exploration through iterative action generation. However, the stochasticity of diffusion policies is not suitable for stable and precise control in high-dimensional robotic systems, where small action variations can accumulate into inconsistent motion and reduced robustness. To address this issue, we propose SteerGenPO, a latent-space reinforcement learning framework that steers a trained generative policy into a robust deterministic robotic controller. The key idea is to replace stochastic latent sampling of the trained generative policy with a learned latent actor that predicts a state-dependent latent input for the generative policies. This separates exploration and control: stochastic generative sampling provides diverse action proposals during policy learning, while deterministic latent steering provides stable and adaptive control at deployment. We evaluate SteerGenPO on six Isaac Lab benchmarks and a Unitree G1 locomotion task. The results show SteerGenPO improves over both classical RL and generative RL baselines, while its deterministic latent steering produces more stable inference-time behaviors and more reliable command responses.

📄 PDF Abstract BibTeX arXiv:2606.16572

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies

2026-05-31 · Hikmet Simsir, Ozgur S. Oguz arxiv

Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift. Direct reinforcement learning fine-tuning can improve …

Reinforcement LearningOpenAI Gym

A Novel Sample-efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Cardiac Catheterization Robots

2021-10-28 · Olatunji Mumini Omisore, Toluwanimi Akinyemi, Wenke Duan, Wenjing Du 외

Robotic catheterization is typically used for percutaneous coronary intervention procedures nowadays and it involves steering flexible endovascular tools to open up occlusion in the coronaries. In this study, a sample-ef…

Deep Reinforcement Learning

Symmetry-Aware Steering of Equivariant Diffusion Policies: Benefits and Limits

2025-12-12 · Minwoo Park, Junwoo Chang, Jongeun Choi, Roberto Horowitz arxiv

Equivariant diffusion policies (EDPs) combine the generative expressivity of diffusion models with the strong generalization and sample efficiency afforded by geometric symmetries. While steering these policies with rein…

Reinforcement Learning

Latent Policy Steering through One-Step Flow Policies

2026-03-05 · Hokyun Im, Andrey Kolobov, Jianlong Fu, Youngwoon Lee arxiv

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can pus…

Reinforcement LearningOffline RL

RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation

2026-02-02 · Entong Su, Tyler Westenbroek, Anusha Nagabandi, Abhishek Gupta arxiv

Imitation learning has emerged as an effective approach for bootstrapping sequential decision-making in robotics, achieving strong performance even in high-dimensional dexterous manipulation tasks. Recent behavior clonin…

Reinforcement Learning