ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
cs.RO, cs.AI, cs.LG
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: Project website: https://accrue-rl.github.io
Project page: https://accrue-rl.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- On Tiny Episodic Memories in Continual Learning
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
- GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
- Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
- FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- CRL-VLA: Continual Vision-Language-Action Learning
- Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies