arXiv AI September 18, 2026 By Yilang Liu, Haoxiang You, Qian Wang, Daniel Rakita, Ian Abraham

Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control

The paper introduces Sampling-Guided Policy Search (SGPS), a method that combines sampling-based model‑predictive control with first‑order policy gradients to accelerate visual policy learning for locomotion and manipulation tasks. SGPS starts with behavior cloning from sampled actions and then alternates between sampling‑based refinement and short‑horizon policy updates under varied initial states and dynamics. The approach is demonstrated on simulated Unitree Go2 and G1 robots, learning tasks such as obstacle traversal and bimanual carrying, and the distilled policies transfer zero‑shot to a real Go2 robot using onboard depth perception.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

robotics

arXiv Machine Learning

Jul 31

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

arXiv:2603. 13707v3 Announce Type: replace-cross Abstract: Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks.

By Zhaoyuan Gu, Yipu Chen, Zimeng Chai, Alfred Cueva, Thong Nguyen, Yifan Wu, Huishu Xue, Minji Kim, Isaac Legene, Fukang Liu, KyoungMok Kim, Ayan Barula, Yongxin Chen, Ye Zhao

diffusion reinforcement-learning robotics fine-tuning

arXiv AI

Aug 13

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

arXiv:2605. 12236v2 Announce Type: replace-cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.

By Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta

agents diffusion reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Jun 29

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.

By Raymond Yu, William Huey, Mustafa Mukadam, Anusha Nagabandi, Abhishek Gupta

reinforcement-learning robotics efficiency

arXiv Machine Learning

Sep 7

Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics

Squint is a visual Soft Actor Critic algorithm designed to accelerate reinforcement learning for robotics. It combines parallel simulation, a distributional critic, resolution squinting, layer normalization, a tuned update-to-data ratio, and an optimized implementation to reduce wall‑clock training time. On the SO‑101 Task Set, Squint trains policies in as little as 15 minutes on a single RTX 3090 GPU, with most tasks converging in under 6 minutes and successfully transferring to a real SO‑101 robot.

By Abdulaziz Almuzairee, Henrik I. Christensen

reinforcement-learning robotics

arXiv AI

Jul 21

Predictive Training with Latent Imagination for Visual Quadruped Navigation

arXiv:2607. 17574v1 Announce Type: cross Abstract: Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory, with limited capacity to anticipate how moving obstacles will evolve in the near future.

By Yancheng Zhu, Wanli Ma, Chen Han, Irvin Haozhe Zhan, Bingfeng Qin, Yixin Xu

robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 9

Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking

arXiv:2606. 08253v1 Announce Type: cross Abstract: Enabling humanoid robots to operate in complex, dynamic environments remains a critical challenge, fundamentally limited by the ability to navigate robustly, safely, and accurately.

By Alessandro Montenegro, Shihao Li, Puze Liu, Alberto Maria Metelli, Jan Peters

computer-vision reinforcement-learning robotics

One email a morning, machine-written

Related stories

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics

Predictive Training with Latent Imagination for Visual Quadruped Navigation

Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking