Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
cs.LG, cs.RO
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/lasgroup/generalist-improvement
Project page: https://lasgroup.github.io/generalist-improvement
Terminology
Sources
- Robotic Policy Adaptation via Weight-Space Meta-Learning
- When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
- Improving Vision-Language-Action Model with Online Reinforcement Learning
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
- GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
- OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis