# ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations

arXiv: https://arxiv.org/abs/2505.10911 · HTML: https://mlsanity.com/paper/2505.10911/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 16 May 2025.

## Placed in

- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Built on by (most cited first, 30 of 60)

- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics](https://mlsanity.com/paper/2602.19313/) (2026)
- [EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models](https://mlsanity.com/paper/2512.14666/) (2025)
- [RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2511.01331/) (2025)
- [Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.10503/) (2026)
- [chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies](https://mlsanity.com/paper/2602.09021/) (2026)
- [ARM: Advantage Reward Modeling for Long-Horizon Manipulation](https://mlsanity.com/paper/2604.03037/) (2026)
- [OpenGVL -- Benchmarking Visual Temporal Progress for Data Curation](https://mlsanity.com/paper/2509.17321/) (2025)
- [Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models](https://mlsanity.com/paper/2602.12628/) (2026)
- [ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation](https://mlsanity.com/paper/2605.08774/) (2026)
- [RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance](https://mlsanity.com/paper/2608.09853/) (2026)
- [From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2603.15600/) (2026)
- [Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation](https://mlsanity.com/paper/2603.15759/) (2026)
- [TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation](https://mlsanity.com/paper/2605.25547/) (2026)
- [Progress Reward Modeling for Robotic Learning: A Comprehensive Survey](https://mlsanity.com/paper/2607.21655/) (2026)
- [AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations](https://mlsanity.com/paper/2511.18617/) (2025)
- [OMP: One-step Meanflow Policy with Directional Alignment](https://mlsanity.com/paper/2512.19347/) (2025)
- [AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization](https://mlsanity.com/paper/2603.23566/) (2026)
- [SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning](https://mlsanity.com/paper/2603.28730/) (2026)
- [RDA: Reward Design Agent for Reinforcement Learning](https://mlsanity.com/paper/2606.01672/) (2026)
- [RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation](https://mlsanity.com/paper/2606.22027/) (2026)
- [AURA: Autonomous Upskilling with Retrieval-Augmented Agents](https://mlsanity.com/paper/2506.02507/) (2025)
- [Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress](https://mlsanity.com/paper/2509.24129/) (2025)
- [Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models](https://mlsanity.com/paper/2603.16978/) (2026)
- [SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation](https://mlsanity.com/paper/2606.10305/) (2026)
- [InSight: Self-Guided Skill Acquisition via Steerable VLAs](https://mlsanity.com/paper/2606.24884/) (2026)

## Abstract (arXiv)

We introduce ReWiND, a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. Standard reinforcement learning (RL) and imitation learning methods require expert supervision through human-designed reward functions or demonstrations for every new task. In contrast, ReWiND starts from a small demonstration dataset to learn: (1) a data-efficient, language-conditioned reward function that labels the dataset with rewards, and (2) a language-conditioned policy pre-trained with offline RL using these rewards. Given an unseen task variation, ReWiND fine-tunes the pre-trained policy using the learned reward function, requiring minimal online interaction. We show that ReWiND's reward model generalizes effectively to unseen tasks, outperforming baselines by up to 2.4x in reward generalization and policy alignment metrics. Finally, we demonstrate that ReWiND enables sample-efficient adaptation to new tasks, beating baselines by 2x in simulation and improving real-world pretrained bimanual policies by 5x, taking a step towards scalable, real-world robot learning. See website at https://rewind-reward.github.io/.