English
Related papers

Related papers: Optimization Issues in KL-Constrained Approximate …

200 papers

Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to value maximization, other practical considerations arise as…

Machine Learning · Computer Science 2023-01-12 Wenhao Zhan , Shicong Cen , Baihe Huang , Yuxin Chen , Jason D. Lee , Yuejie Chi

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

Machine Learning · Computer Science 2025-07-08 Buqing Nie , Yangqing Fu , Jingtian Ji , Yue Gao

Group Relative Policy Optimization (GRPO) is widely used for critic-free Large Language Model (LLM) post-training, but its KL regularization is usually implemented as a local loss-side token penalty. We show that this misses the…

Machine Learning · Computer Science 2026-05-26 Jiarui Yao , Ruida Wang , Hao Bai , Tong Zhang

Self-play alignment has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regularization with respect to the reference policy, which is…

Machine Learning · Computer Science 2025-07-09 Xiaohang Tang , Sangwoong Yoon , Seongho Son , Huizhuo Yuan , Quanquan Gu , Ilija Bogunovic

Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start…

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 step size at each…

Machine Learning · Computer Science 2020-12-07 Wangshu Zhu , Andre Rosendo

Lexicographic multi-objective problems, which impose a lexicographic importance order over the objectives, arise in many real-life scenarios. Existing Reinforcement Learning work directly addressing lexicographic tasks has been scarce. The…

Machine Learning · Computer Science 2024-09-05 Alperen Tercan , Vinayak S. Prabhu

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving…

Machine Learning · Computer Science 2025-12-23 Pierre-François Massiani , Alexander von Rohr , Lukas Haverbeck , Sebastian Trimpe

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

We present a proximal policy optimization (PPO) agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of…

Machine Learning · Computer Science 2024-07-24 Abhijeet Pendyala , Asma Atamna , Tobias Glasmachers

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…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Zhe Wu , Junliang Xing

Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization in the stochastic setting. This problem corresponds to the minimization of the sum of a (weakly) smooth function endowed…

Machine Learning · Computer Science 2024-01-24 Alexandre d'Aspremont , Cristóbal Guzmán , Clément Lezane

We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined…

Optimization and Control · Mathematics 2024-01-02 Dongsheng Ding , Zhengyan Huan , Alejandro Ribeiro

The infinite horizon setting is widely adopted for problems of reinforcement learning (RL). These invariably result in stationary policies that are optimal. In many situations, finite horizon control problems are of interest and for such…

Machine Learning · Computer Science 2025-03-21 Soumyajit Guin , Shalabh Bhatnagar

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

Over the past few years, the acceleration of computing resources and research in deep learning has led to significant practical successes in a range of tasks, including in particular in computer vision. Building on these advances,…

Artificial Intelligence · Computer Science 2022-04-14 David Bertoin , Emmanuel Rachelson

Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However, there is a significant disconnect between the underlying…

Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g.,…

Machine Learning · Computer Science 2026-03-09 Xiaocan Li , Shiliang Wu , Zheng Shen
‹ Prev 1 4 5 6 7 8 10 Next ›