paper-with-me

Papers

Variational Proximal Policy Optimization

2026-06-06 · Ousmane Amadou Dia arxiv

Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and distribution drift. This paper introduces Variational Proximal Policy Optimization (\(\textsc{VP}_2\textsc{O}\)), a particle-based variational inference framework that maps policy optimization to Stein Variational Gradient Descent within a Mixture-of-Experts architecture. By leveraging functional kernels over localized expert prototypes alongside an expert orthogonalization loss, \(\textsc{VP}_2\textsc{O}\) introduces a geometry-based proximal-control mechanism that can reduce reliance on fixed clipping or KL schedules. Our results on a 33B/4B sparse Mixture-of-Experts model show several improvements across complex reasoning benchmarks, establishing a \(+\mathbf{179}\) ELO gain on Codeforces and a \(\mathbf{32\%}\) reduction in token count on AIME mathematical reasoning tasks.

📄 PDF Abstract BibTeX arXiv:2606.08032

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMathematical Reasoning

Similar Papers 제목 키워드 기반

CuRLA: Curriculum Learning Based Deep Reinforcement Learning for Autonomous Driving

2025-01-09 · Bhargava Uppuluri, Anjel Patel, Neil Mehta, Sridhar Kamath 외

In autonomous driving, traditional Computer Vision (CV) agents often struggle in unfamiliar situations due to biases in the training data. Deep Reinforcement Learning (DRL) agents address this by learning from experience…

Autonomous DrivingDeep Reinforcement Learningreinforcement-learningReinforcement Learning

Riemannian Proximal Policy Optimization

2020-05-19 · Shijun Wang, Baocheng Zhu, Chen Li, Mingzhe Wu 외

In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture mod…

Proximal Policy Optimization with Mixed Distributed Training

2019-07-15 · Zhen-Yu Zhang, Xiangfeng Luo, Tong Liu, Shaorong Xie 외

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algori…

Deep Reinforcement LearningReinforcement Learning

ERPPO: Entropy Regularization-based Proximal Policy Optimization

2026-05-13 · Changha Lee, Gyusang Cho arxiv

Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent reinforcement learning (MARL). MAPPO optimizes cooperative multi-ag…

Multi-agent Reinforcement LearningObject LocalizationObject Detection

Generalized Proximal Policy Optimization with Sample Reuse

2021-10-29 · NeurIPS 2021 12 · James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout train…

Decision Making