paper-with-me

Papers

Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation

2025-05-16 · Donghoon Lee, Tung M. Luu, Younghwan Lee, Chang D. Yoo

Recent research highlights the potential of multimodal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained systems. Reinforcement learning (RL) shows promise for task-specific agents but suffers from high sample complexity, limiting practical applications. To address these challenges, we introduce LVLM to Policy (LVLM2P), a novel framework that distills knowledge from large vision-language models (LVLM) into more efficient RL agents. Our approach leverages the LVLM as a teacher, providing instructional actions based on trajectories collected by the RL agent, which helps reduce less meaningful exploration in the early stages of learning, thereby significantly accelerating the agent's learning progress. Additionally, by leveraging the LVLM to suggest actions directly from visual observations, we eliminate the need for manual textual descriptors of the environment, enhancing applicability across diverse tasks. Experiments show that LVLM2P significantly enhances the sample efficiency of baseline RL algorithms.

📄 PDF Abstract BibTeX arXiv:2505.11221

Code (1)

i22024/lvlm2p 공식 구현 pytorch

Tasks

Decision MakingLanguage ModelingLanguage ModellingReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

2026-07-25 · Shuai Wang, Daoan Zhang, Zhe Tang, Hao Cheng 외 arxiv

Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods usually rely on human-annotated data, distillation from external mo…

Reinforcement LearningVisual Reasoning

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

2026-07-16 · Jinyang Wu, Shuo Yang, Zhengxi Lu, Fan Zhang 외 arxiv

Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a pract…

Reinforcement LearningDecision Making

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

2026-04-02 · Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignmen…

Reinforcement Learning

Distilled Reinforcement Learning for LLM Post-training

2026-07-19 · Chen Wang, Zhaochun Li, Jionghao Bai, Yining Zhang 외 hf

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). Howeve…

Reinforcement Learning

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

2026-04-12 · Binbin Zheng, Xing Ma, Yiheng Liang, Jingqing Ruan 외 arxiv

On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult. On-Polic…

Reinforcement Learning