StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks

arXiv:2609.36352 · cs.CV, cs.LG, cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.LG, cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/amazon-science/StructRL

Terminology

• Benchmark — 24× in this paper · explained in 2 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Verifiability — 6× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• VLA Models — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Online Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Action Flow — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In Conference on Robot Learning — 1× in this paper
• Proximal Policy Optimization (PPO) — 1× in this paper · explained in 5 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• VLA with Proximal Policy Optimization — 1× in this paper
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Qwen3-VL Technical Report
• $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
• Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models