Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

• URL: http://arxiv.org/abs/2603.16065v1
• Date: Tue, 17 Mar 2026 02:22:16 GMT
• Title: Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
• Abstract summary: We develop a robust, scalable reward model based on a state-of-the-art VLM.<n>We employ these VLM rewards to guide the model to correct sub-optimal behaviors in a closed-loop manner.
• Score: 19.819472980239826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a framework for online policy refinement by adapting foundation VLMs into online reward generators. We develop a robust, scalable reward model based on a state-of-the-art VLM, trained on a large-scale, multi-source dataset encompassing real-world robot trajectories, human-object interactions, and diverse simulated environments. Unlike prior approaches that evaluate entire trajectories post-hoc, our method leverages the VLM to formulate a multifaceted reward signal comprising process, completion, and temporal contrastive rewards based on current visual observations. Initializing with a base policy trained via Imitation Learning (IL), we employ these VLM rewards to guide the model to correct sub-optimal behaviors in a closed-loop manner. We evaluate our framework on challenging long-horizon manipulation benchmarks requiring sequential execution and precise control. Crucially, our reward model operates in a purely zero-shot manner within these test environments. Experimental results demonstrate that our method significantly improves the success rate of the initial IL policy within just 30 RL iterations, demonstrating remarkable sample efficiency. This empirical evidence highlights that VLM-generated signals can provide reliable feedback to resolve execution errors, effectively eliminating the need for manual reward engineering and facilitating efficient online refinement for robot learning.

Related papers

• Q-Learning With World Models [69.63968749241239]
  We propose a framework that leverages world models to perform test-time search over imagined trajectories on top of Q-learning to select high-value actions.<n>QWM significantly outperforms strong prior state-of-the-art methods on both sample efficiency and performance.
  arXiv  Detail & Related papers  (2026-08-17T22:00:42Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• Reinforcement World Model Learning for LLM-based Agents [60.65003139516272]
  Reinforcement World Model Learning (RWML) is a self-conditioned method that learns action-supervised world models for LLM-based agents.<n>Our method aligns simulated next states produced by the model with realized next states observed from the environment.<n>We evaluate our method on ALFWorld and $2$ Bench and observe significant gains over the base model, despite being entirely self-supervised.
  arXiv  Detail & Related papers  (2026-02-05T16:30:08Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Leveraging LLMs for reward function design in reinforcement learning control tasks [0.0]
  This paper introduces LEARN-Opt (LLM-based Evaluator and Analyzer for Reward functioN Optimization)<n>This framework generates, execute, and evaluate reward function candidates from textual descriptions of systems and task objectives.<n>Our experiments indicate that LEARN-Opt achieves performance comparable to or better to that of state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-24T17:55:46Z)
• Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs [72.08224879435762]
  textttLearn-to-Ask is a simulator-free framework for learning and deploying proactive dialogue agents.<n>Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service.
  arXiv  Detail & Related papers  (2025-10-29T12:08:07Z)
• Policy Learning from Large Vision-Language Model Feedback without Reward Modeling [19.48826538310603]
  We introduce PLARE, a novel approach that leverages large vision-language models (VLMs) to provide guidance signals for agent training.<n>Instead of relying on manually designed reward functions, PLARE queries a VLM for preference labels on pairs of visual trajectory segments.<n>The policy is then trained directly from these preference labels using a supervised contrastive preference learning objective.
  arXiv  Detail & Related papers  (2025-07-31T10:07:49Z)
• VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning [14.099306230721245]
  We present VLA-RL, an exploration-based framework that improves on online collected data at test time.<n>We fine-tune a pretrained vision-language model as a robotic process reward model, which is trained on pseudo reward labels annotated on automatically extracted task segments.<n>VLA-RL enables OpenVLA-7B to surpass the strongest finetuned baseline by 4.5% on 40 challenging robotic manipulation tasks in LIBERO.
  arXiv  Detail & Related papers  (2025-05-24T14:42:51Z)
• Affordance-Guided Reinforcement Learning via Visual Prompting [51.361977466993345]
  Keypoint-based Affordance Guidance for Improvements (KAGI) is a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL.<n>On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps.
  arXiv  Detail & Related papers  (2024-07-14T21:41:29Z)
• RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback [24.759613248409167]
  Reward engineering has long been a challenge in Reinforcement Learning research. We propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains.
  arXiv  Detail & Related papers  (2024-02-06T04:06:06Z)
• MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning [52.101643259906915]
  We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations. Existing model-based offline RL methods are not suitable for offline-to-online fine-tuning in high-dimensional domains. We propose an on-policy model-based method that can efficiently reuse prior data through model-based value expansion and policy regularization.
  arXiv  Detail & Related papers  (2024-01-06T21:04:31Z)
• SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
  This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision. We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
  arXiv  Detail & Related papers  (2023-10-09T17:56:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.