Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

• URL: http://arxiv.org/abs/2405.10292v3
• Date: Mon, 07 Oct 2024 19:13:47 GMT
• Title: Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
• Authors: Yuexiang Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Shengbang Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, Sergey Levine,
• Abstract summary: 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.
• Score: 79.38140606606126
• License:
• Abstract: Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.

Related papers

• EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications. Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• On the Modeling Capabilities of Large Language Models for Sequential Decision Making [52.128546842746246]
  Large pretrained models are showing increasingly better performance in reasoning and planning tasks. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly. In environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities.
  arXiv  Detail & Related papers  (2024-10-08T03:12:57Z)
• VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs [38.03704123835915]
  Large-scale generative language and vision-language models excel in in-context learning for decision making. We propose In-Context Abstraction Learning (ICAL), a method that builds a memory of multimodal experience from sub-optimal demonstrations and human feedback. Our approach significantly reduces reliance on manual prompt engineering and consistently outperforms in-context learning from action plans that lack such abstractions.
  arXiv  Detail & Related papers  (2024-06-20T17:45:02Z)
• Meta Reasoning for Large Language Models [58.87183757029041]
  We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) MRP guides LLMs to dynamically select and apply different reasoning methods based on the specific requirements of each task. We evaluate the effectiveness of MRP through comprehensive benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T16:14:11Z)
• Exploring the Transferability of Visual Prompting for Multimodal Large Language Models [47.162575147632396]
  Transferable Visual Prompting (TVP) is a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts.
  arXiv  Detail & Related papers  (2024-04-17T09:39:07Z)
• OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following [38.99303334457817]
  Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions. Recent advancements have seen a surge in employing large language models (LLMs) within a framework-centric approach to enhance performance in EIF. We introduce OPEx, a comprehensive framework that delineates the core components essential for solving EIF tasks: Observer, Planner, and Executor.
  arXiv  Detail & Related papers  (2024-03-05T14:53:53Z)
• Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models [41.38520841504846]
  Large language models (LLMs) can provide automated preference feedback solely from image inputs to guide decision-making. In this study, we train a multimodal LLM, termed CriticGPT, capable of understanding trajectory videos in robot manipulation tasks. Experimental evaluation of the algorithm's preference accuracy demonstrates its effective generalization ability to new tasks. Performance on Meta-World tasks reveals that CriticGPT's reward model efficiently guides policy learning, surpassing rewards based on state-of-the-art pre-trained representation models.
  arXiv  Detail & Related papers  (2024-02-22T03:14:03Z)
• u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
  u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
  arXiv  Detail & Related papers  (2023-11-09T13:18:27Z)
• Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
  Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes. We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
  arXiv  Detail & Related papers  (2023-09-30T07:11:39Z)
• Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models [61.28463542324576]
  Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can generate human-like outputs. We evaluate existing state-of-the-art VLMs and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency. We propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs.
  arXiv  Detail & Related papers  (2023-09-08T17:49:44Z)

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.