# Real-World Offline Reinforcement Learning from Vision Language Model Feedback

arXiv: https://arxiv.org/abs/2411.05273 · HTML: https://mlsanity.com/paper/2411.05273/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 37 of its 43 references that are in the map.
- First posted on arXiv 8 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning](https://mlsanity.com/paper/2310.12921/) (2023)
- [Text2Reward: Reward Shaping with Language Models for Reinforcement Learning](https://mlsanity.com/paper/2309.11489/) (2023)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/2011.07215/) (2020)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)

## Built on by (most cited first, 22 of 22)

- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning](https://mlsanity.com/paper/2508.13904/) (2025)
- [ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks](https://mlsanity.com/paper/2508.01943/) (2025)
- [TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation](https://mlsanity.com/paper/2605.25547/) (2026)
- [Policy Learning from Large Vision-Language Model Feedback without Reward Modeling](https://mlsanity.com/paper/2507.23391/) (2025)
- [SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning](https://mlsanity.com/paper/2603.28730/) (2026)
- [LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning](https://mlsanity.com/paper/2504.15472/) (2025)
- [Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions](https://mlsanity.com/paper/2509.12741/) (2025)
- [MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models](https://mlsanity.com/paper/2602.15872/) (2026)
- [Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning](https://mlsanity.com/paper/2606.10613/) (2026)
- [DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation](https://mlsanity.com/paper/2607.13033/) (2026)
- [Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models](https://mlsanity.com/paper/2503.16724/) (2025)
- [Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossing](https://mlsanity.com/paper/2504.08704/) (2025)
- [GenDexHand: Generative Simulation for Dexterous Hands](https://mlsanity.com/paper/2511.01791/) (2025)
- [Inference Time Policy Optimization for Offline RL with Differentiable World Models](https://mlsanity.com/paper/2603.22430/) (2026)
- [Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations](https://mlsanity.com/paper/2605.22123/) (2026)
- [Learning Process Rewards via Success Visitation Matching for Efficient RL](https://mlsanity.com/paper/2606.23640/) (2026)
- [NatSGLD: A Dataset with Speech, Gesture, Logic, and Demonstration for Robot Learning in Natural Human-Robot Interaction](https://mlsanity.com/paper/2502.16718/) (2025)
- [VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning](https://mlsanity.com/paper/2607.00483/) (2026)
- [CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning](https://mlsanity.com/paper/2607.01721/) (2026)
- [HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation](https://mlsanity.com/paper/2607.09776/) (2026)
- [Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models](https://mlsanity.com/paper/2609.05401/) (2026)

## Abstract (arXiv)

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert demonstrations is slow, costly, and risky. However, most existing offline RL works assume the dataset is already labeled with the task rewards, a process that often requires significant human effort, especially when ground-truth states are hard to ascertain (e.g., in the real-world). In this paper, we build on prior work, specifically RL-VLM-F, and propose a novel system that automatically generates reward labels for offline datasets using preference feedback from a vision-language model and a text description of the task. Our method then learns a policy using offline RL with the reward-labeled dataset. We demonstrate the system's applicability to a complex real-world robot-assisted dressing task, where we first learn a reward function using a vision-language model on a sub-optimal offline dataset, and then we use the learned reward to employ Implicit Q learning to develop an effective dressing policy. Our method also performs well in simulation tasks involving the manipulation of rigid and deformable objects, and significantly outperform baselines such as behavior cloning and inverse RL. In summary, we propose a new system that enables automatic reward labeling and policy learning from unlabeled, sub-optimal offline datasets.