paper-with-me

홈 › Papers

Flow Policy Gradients for Robot Control

2026-02-02 · Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh, Xiaoyu Huang, Takara E. Truong, Carmelo Sferrazza, Yi Ma, Rocky Duan, Pieter Abbeel, Guanya Shi, Karen Liu, Angjoo Kanazawa arxiv

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like Gaussians. In this work, we show how flow matching policy gradients -- a recent framework that bypasses likelihood computation -- can be made effective for training and fine-tuning more expressive policies in challenging robot control settings. We introduce an improved objective that enables success in legged locomotion, humanoid motion tracking, and manipulation tasks, as well as robust sim-to-real transfer on two humanoid robots. We then present ablations and analysis on training dynamics. Results show how policies can exploit the flow representation for exploration when training from scratch, as well as improved fine-tuning robustness over baselines.

📄 PDF Abstract BibTeX arXiv:2602.02481

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

2026-06-19 · Ge Wang, Yibo Peng, Fan Feng, Shenhao Yan 외 arxiv

We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We uncover a key structural property: the …

Physical Simulations

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

2025-09-30 · Yixian Zhang, Shu'ang Yu, Tonghe Zhang, Mo Guang 외 arxiv

Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental con…

Reinforcement LearningContinuous Control

Provably Robust Blackbox Optimization for Reinforcement Learning

2019-03-07 · Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang 외

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for p…

MuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Shape Your Body: Value Gradients for Multi-Embodiment Robot Design

2026-05-30 · Nico Bohlinger, Jan Peters arxiv

We propose to turn generalist multi-embodiment value functions into reusable models for robot design. Instead of running a new reinforcement learning co-design loop for each robot, we first train an embodiment-aware poli…

Reinforcement Learning

Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution

2017-08-01 · ICML 2017 8 · Po-Wei Chou, Daniel Maturana, Sebastian Scherer

Recently, reinforcement learning with deep neural networks has achieved great success in challenging continuous control problems such as 3D locomotion and robotic manipulation. However, in real-world control problem…

continuous-controlContinuous ControlDeep Reinforcement LearningReinforcement Learning