Proximal policy optimization (PPO)

area: Machine learning · 1 papers in the last 7 days

L(\theta) = E_t\big[\min\big(r_t(\theta)\hat A_t,\ \mathrm{clip}(r_t(\theta), 1 - \epsilon, 1 + \epsilon)\,\hat A_t\big)\big]

Policy-gradient reinforcement learning with a clipped objective that keeps updates small.

LaTeX: L(\theta) = E_t\big[\min\big(r_t(\theta)\hat A_t,\ \mathrm{clip}(r_t(\theta), 1 - \epsilon, 1 + \epsilon)\,\hat A_t\big)\big]

Names searched for: proximal policy optimization, proximal policy optimisation, PPO

Key findings

Proximal policy optimization (PPO) was mentioned in 17 papers in the last 30 days (2026-09-27 to 2026-10-26), ranking #51 of the 104 equations and models mentioned.
By journal category: AI (9), Operations Research (7) and Economics (1).
Most of them appeared in Expert Systems with Applications (2), Applied Intelligence (2) and Annals of Operations Research (2).
Often mentioned together with Q-learning (4), Scaled dot-product attention (Transformer) (4) and Linear and integer programming (3).
Datasets named in the same papers: OR-Library (2), MNIST / Fashion-MNIST (1) and UCI Machine Learning Repository (1).

Papers mentioning Proximal policy optimization (PPO), newest first.
Date	Title	Journal	Authors	Affiliations
2026-10-24	Subsidy-Effectiveness Inversion in Green FDI: Dynamic Portfolio Optimization under Supply Chain Complementarity	Computational Economics	Rongliang Xu, Tianming Xu	Central South University
2026-10-17	A two-stage ensemble learning framework for imbalanced classification via feature and ensemble selection	Expert Systems with Applications	Pengcheng Liu	Southwest Jiaotong University
2026-10-17	MO-UDRL-H: hybrid Pareto-safe distributional reinforcement learning for multi-objective cloud task allocation	Applied Intelligence	Chunhui Xu, Chundi Hu	Zhejiang Ocean University
2026-10-17	D-MAPPO-ABC: distributed multi-agent proximal policy optimization enhanced with artificial bee colony for edge computing task scheduling	Annals of Operations Research	Muhammed Şara, Koray Ozdemir, Süleyman Eken et al.	Kocaeli Üniversitesi; Yalova University
2026-10-09	A reinforcement learning-based EWMA control chart with an application to urban mobility monitoring	Computers & Industrial Engineering	Usman Ibrahim, Mohammad M. AlDurgam, Nasir Abbas et al.	King Fahd University of Petroleum and Minerals
2026-10-08	JTCSE: Joint tensor-modulus constraints and cross-attention for unsupervised contrastive learning of sentence embeddings	Neural Networks	Tianyu Zong, Bingkang Shi, Hongzhu Yi et al.	University of Chinese Academy of Sciences
2026-10-05	Spatio-temporal graph reinforcement learning for multi-period supply chain synchronization: Joint procurement, warehousing, and multimodal routing with multiple 3PL providers	Computers & Operations Research	Jinjin Cai, Rui Song, 何世伟 et al.	Beijing Jiaotong University
2026-10-02	RL-Axial: Learning When to Compute Global Context for Multimodal Segmentation	Cognitive Computation	Dong Xing, Hang Yang, Jinhe Zhang et al.	Chinese Academy of Sciences; Changchun Institute of Optics, Fine Mechanics and Physics; University of Chinese Academy of Sciences
2026-10-01	Knowledge-Driven Optimization and Recurrent Deep Reinforcement Learning for Lean Batch Scheduling in Cutting Tool Manufacturing	Expert Systems with Applications	Siwei Fu, Mats Gustafsson, Sunith Bandaru et al.	University of Skövde; Uppsala University
2026-10-01	RLAX: A Reinforcement Learning-Based Framework for Explaining Anomalous Data	Machine Learning	Simone Amirato, Fabrizio Angiulli, Fabio Fassetti	University of Calabria
2026-10-01	GDPB: a gradient-decoupled privileged baseline for UAV navigation under compound disturbances	Applied Intelligence	Xin Wang, 赵健康	Shanghai Jiao Tong University
2026-10-01	Benchmarking adaptive pricing policies for Mississippi River container-on-barge service	Annals of Operations Research	Alex Carroll	Massachusetts Institute of Technology
2026-09-30	Solution methods for the dynamic and probabilistic profitable tour problem	OR Spectrum	Marvin Caspar, Daniel Schermer, Oliver Wendt	University of Kaiserslautern; Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
2026-09-29	A Deep Reinforcement learning model for centralized route recommendation in multi-modal transit networks	Transportation Research Part E Logistics and Transportation Review	Zijian Shen, Taijie Chen, Bin Zhou et al.	University of Hong Kong
2026-09-28	FreSia: Frequency-semantic instantiation and alignment for multivariate time series analysis	Pattern Recognition	Yubo Wang, Hui He, Hezhe Qiao et al.	Beijing Institute of Technology; Singapore Management University
2026-09-28	Distributed order allocation in social additive manufacturing factory clusters using multi-agent reinforcement learning	Computers & Industrial Engineering	Inno Lorren Désir Makanda, Maolin Yang, Pingyu Jiang	Xi'an Jiaotong University
2026-09-28	Minute-scale training for microrobot navigation	Nature Machine Intelligence	Yinghan Sun, Aoji Zhu, Xiang Ji et al.	Hong Kong Polytechnic University; Chinese University of Hong Kong; Harbin Institute of Technology