paper-with-me

Papers

An Adaptive Clipping Approach for Proximal Policy Optimization

2018-04-17 · Gang Chen, Yiming Peng, Mengjie Zhang

Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves data efficiency by performing multiple epochs of \emph{clipped policy optimization} from sampled data. Although clipping in PPO stands for an important new mechanism for efficient and reliable policy update, it may fail to adaptively improve learning performance in accordance with the importance of each sampled state. To address this issue, a new surrogate learning objective featuring an adaptive clipping mechanism is proposed in this paper, enabling us to develop a new algorithm, known as PPO-$\lambda$. PPO-$\lambda$ optimizes policies repeatedly based on a theoretical target for adaptive policy improvement. Meanwhile, destructively large policy update can be effectively prevented through both clipping and adaptive control of a hyperparameter $\lambda$ in PPO-$\lambda$, ensuring high learning reliability. PPO-$\lambda$ enjoys the same simple and efficient design as PPO. Empirically on several Atari game playing tasks and benchmark control tasks, PPO-$\lambda$ also achieved clearly better performance than PPO.

📄 PDF Abstract BibTeX arXiv:1804.06461

Code (0)

등록된 구현이 없습니다.

Tasks

Learning TheoryReinforcement Learning

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

A dynamical clipping approach with task feedback for Proximal Policy Optimization

2023-12-12 · Ziqi Zhang, Jingzehua Xu, Zifeng Zhuang, Hongyin Zhang 외

Proximal Policy Optimization (PPO) has been broadly applied to robotics learning, showcasing stable training performance. However, the fixed clipping bound setting may limit the performance of PPO. Specifically, there is…

Language ModellingLarge Language ModelMuJoCoReinforcement Learning (RL)

Proximal Policy Optimization Smoothed Algorithm

2020-12-04 · Wangshu Zhu, Andre Rosendo

Proximal policy optimization (PPO) has yielded state-of-the-art results in policy search, a subfield of reinforcement learning, with one of its key points being the use of a surrogate objective function to restrict the s…

continuous-controlContinuous Control

ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning

2025-10-01 · Yunhao Wang, Ziting Li, Shuai Chen, Tao Liu 외 arxiv

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and t…

Reinforcement LearningMultimodal Reasoning

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

2026-06-09 · Bowen Ping, Xiangxin Zhou, Penghui Qi, Minnan Luo 외 arxiv

Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the …

Reinforcement LearningVideo Generation

Decaying Clipping Range in Proximal Policy Optimization

2021-02-20 · Mónika Farsang, Luca Szegletes

Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable po…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)