Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning

• URL: http://arxiv.org/abs/2509.21126v1
• Date: Thu, 25 Sep 2025 13:16:34 GMT
• Title: Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning
• Authors: Xiefeng Wu, Jing Zhao, Shu Zhang, Mingyu Hu,
• Abstract summary: Vision-language action (VLA) policies represent a promising direction for solving diverse tasks.<n>We propose textbf VARL (textbfVLM as textbfAction advisor for online textbfReinforcement textbfL), a framework that leverages the domain knowledge of vision-language models (VLMs) to provide action suggestions for reinforcement learning agents.
• Score: 5.025037011107095
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online reinforcement learning in complex tasks is time-consuming, as massive interaction steps are needed to learn the optimal Q-function.Vision-language action (VLA) policies represent a promising direction for solving diverse tasks; however, their performance on low-level control remains limited, and effective deployment often requires task-specific expert demonstrations for fine-tuning. In this paper, we propose \textbf{VARL} (\textbf{V}LM as \textbf{A}ction advisor for online \textbf{R}einforcement \textbf{L}earning), a framework that leverages the domain knowledge of vision-language models (VLMs) to provide action suggestions for reinforcement learning agents. Unlike previous methods, VARL provides action suggestions rather than designing heuristic rewards, thereby guaranteeing unchanged optimality and convergence. The suggested actions increase sample diversity and ultimately improve sample efficiency, especially in sparse-reward tasks. To validate the effectiveness of VARL, we evaluate it across diverse environments and agent settings. Results show that VARL greatly improves sample efficiency without introducing significant computational overhead. These advantages make VARL a general framework for online reinforcement learning and make it feasible to directly apply reinforcement learning from scratch in real-world environments.

Related papers

• Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization [61.641777037967366]
  Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns.<n>Agentic reinforcement learning (RL) has emerged as a promising solution for training such agents in multi-turn settings.<n>We propose BAO, an agentic RL framework that combines behavior enhancement to enrich proactive reasoning and information-gathering capabilities.
  arXiv  Detail & Related papers  (2026-02-11T20:40:43Z)
• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers [55.33468902405567]
  We propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback.<n>ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision.
  arXiv  Detail & Related papers  (2026-02-09T03:42:16Z)
• A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization [51.27959658504722]
  Multi-task learning offers a principled framework to train these tasks jointly through shared representations.<n>Existing multi-task optimization strategies are primarily guided by training dynamics and often generalize poorly in volatile bidding environments.<n>We present Validation-Aligned Multi-task Optimization (VAMO), which adaptively assigns task weights based on the alignment between per-task training gradients and a held-out validation gradient.
  arXiv  Detail & Related papers  (2025-10-09T03:59:51Z)
• Online Process Reward Leanring for Agentic Reinforcement Learning [92.26560379363492]
  Large language models (LLMs) are increasingly trained with reinforcement learning (RL) as autonomous agents.<n>Recent work attempts to integrate process supervision into agent learning but suffers from biased annotation.<n>We introduce Online Process Reward Learning (OPRL), a general credit-assignment strategy for agentic RL.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance [1.1718316049475228]
  Multi-Agent Systems (MAS) excel at accomplishing complex objectives through the collaborative efforts of individual agents.<n>In this paper, we introduce a novel framework that aims to overcome the challenge of designing an effective reward function.<n>By giving large language models (LLMs) on the prioritization of tasks, our framework generates reward functions that can be dynamically adjusted online.
  arXiv  Detail & Related papers  (2025-07-22T09:26:00Z)
• Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards [50.21528417884747]
  We introduce Omni-Thinker, a unified reinforcement learning framework that enhances large language models (LLMs) performance across diverse tasks.<n>Our approach enables consistent optimization across task types and scales RL-based training to subjective domains.<n> Experimental results across four domains reveal that curriculum learning improves performance by 5.2% over joint training and 9.1% over model merging.
  arXiv  Detail & Related papers  (2025-07-20T01:50:16Z)
• Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation [19.48826538310603]
  We introduce LVLM to Policy (LVLM2P), a framework that distills knowledge from large vision-language models (LVLM) into more efficientReinforcement Learning agents.<n>Our approach leverages the LVLM as a teacher, providing instructional actions based on trajectories collected by the RL agent.<n>We show that LVLM2P significantly enhances the sample efficiency of baseline RL algorithms.
  arXiv  Detail & Related papers  (2025-05-16T13:15:54Z)
• Attention-Augmented Inverse Reinforcement Learning with Graph Convolutions for Multi-Agent Task Allocation [0.29998889086656577]
  Multi-agent task allocation (MATA) plays a vital role in cooperative multi-agent systems.<n>Inverse reinforcement learning (IRL)-based framework is proposed to enhance reward function learning and task execution efficiency.<n>Experiments validate the superiority of the proposed method over widely used multi-agent reinforcement learning (MARL) algorithms.
  arXiv  Detail & Related papers  (2025-04-07T13:14:45Z)
• Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning [38.68600863590734]
  We propose a novel framework, Variational Subgoal-Conditioned Reinforcement Learning (VSC-RL)<n>VSC-RL reformulates the decision-making problem as a variational subgoal-conditioned RL problem with the newly derived optimization objective, Subgoal Evidence Lower BOund.<n>We theoretically and empirically demonstrate that the VSC-RL can efficiently improve the learning efficiency without compromising performance guarantees.
  arXiv  Detail & Related papers  (2025-02-11T20:57:46Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning [79.38140606606126]
  We propose an algorithmic framework that fine-tunes vision-language models (VLMs) with reinforcement learning (RL) Our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning. We demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks.
  arXiv  Detail & Related papers  (2024-05-16T17:50:19Z)
• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience [89.30876995059168]
  inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. This paper addresses the problem of IRL -- inferring the reward function of an agent from observing its behavior.
  arXiv  Detail & Related papers  (2022-08-09T17:29:49Z)

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.