paper-with-me

홈 › Papers

Reflective Policy Optimization

2024-06-06 · Yaozhong Gan, Renye Yan, Zhe Wu, Junliang Xing

On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy Optimization (RPO), a novel on-policy extension that amalgamates past and future state-action information for policy optimization. This approach empowers the agent for introspection, allowing modifications to its actions within the current state. Theoretical analysis confirms that policy performance is monotonically improved and contracts the solution space, consequently expediting the convergence procedure. Empirical results demonstrate RPO's feasibility and efficacy in two reinforcement learning benchmarks, culminating in superior sample efficiency. The source code of this work is available at https://github.com/Edgargan/RPO.

📄 PDF Abstract BibTeX arXiv:2406.03678

Code (1)

edgargan/rpo 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection

2025-12-15 · Zihui Zhao, Zechang Li arxiv

Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large lang…

Reinforcement Learning

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

2025-10-09 · Xiangyu Zhao, Junming Lin, Tianhao Liang, Yifan Zhou 외 arxiv

While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving comple…

Reinforcement LearningResponse Generation

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

2026-08-24 · Jialong Liu, Yuling Shi, Ning Yang, Xiaodong Gu 외 arxiv

Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Models (LLMs) remains …

Mathematical Reasoning

Memento 2: Learning by Stateful Reflective Memory

2025-12-27 · Jun Wang arxiv

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, wit…

Reinforcement Learning

Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation

2026-05-19 · Junjie Wang, Xinghua Lou, Jason Li, Ye Tian 외 arxiv

Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex …