arXiv Computer Vision
AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 10
AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
AtomicVLA is a unified planning-and-execution framework that generates task-level plans, atomic skill abstractions, and fine-grained actions for robotic manipulation. It builds a scalable atomic skill library using a Skill‑Guided Mixture‑of‑Experts (SG‑MoE) and a flexible routing encoder that assigns new skills to dedicated experts, enabling continual learning. Experiments show that AtomicVLA outperforms baseline models on both simulated and real‑world long‑horizon tasks, achieving significant improvements in task performance and learning efficiency.
arXiv Machine Learning
Sep 21
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
The paper introduces PARTS, a real‑world subtask reinforcement learning framework that fine‑tunes a pretrained robot policy by focusing on critical bottleneck subtasks while keeping the base policy frozen. It uses agent‑generated selectors and success verifiers to provide local rewards, enabling learning even when full‑task successes are rare. Experiments on bimanual YAM and single‑arm Franka robots show that PARTS raises complete‑task success from 32% to 61% and from 50% to 95%, respectively, with only tens of minutes of real‑world RL rollouts and minimal human intervention.
arXiv AI
Jun 11
Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents
arXiv:2604. 13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment.
arXiv AI
Aug 19
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
EXPO-FT is a system that enables stable, sample‑efficient reinforcement learning fine‑tuning of pretrained Vision‑Language‑Action (VLA) policies. It achieves perfect success on a range of manipulation tasks—such as routing string lights, striking a pool ball, and inserting a flower into a wine bottle—using only about 19.1 minutes of online robot data. The approach outperforms both RL-from-scratch and existing VLA fine‑tuning methods, and the authors provide an open‑source codebase to support wider adoption.
arXiv Machine Learning
Oct 9
A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control
The paper introduces Success Guided Sampling (SGS), an adaptive sampler that focuses reinforcement learning on task configurations near the policy’s current frontier, thereby reducing wasted experience in massively parallel simulation. SGS enables large‑scale RL to solve complex quadruped locomotion and contact‑rich assembly tasks that previous methods could not, using up to one million parallel environments. The authors also distill the learned policies into RGB‑based models that transfer zero‑shot to real‑world assembly tasks.
arXiv AI
Sep 18
HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface
HIL-UMI is a policy-guided Universal Manipulation Interface that enables robot‑free, human‑in‑the‑loop post‑training of vision‑language‑action models. By querying the current policy during handheld demonstrations and using an Energy Score to detect out‑of‑distribution states, it selectively collects new data and refines a progress‑based advantage estimator. The updated estimator then drives advantage‑conditioned behavioral cloning, improving performance on long‑horizon and precise manipulation tasks while reducing per‑frame collection time compared to HG‑DAgger.