English
Related papers

Related papers: Boosting Trust Region Policy Optimization by Norma…

200 papers

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand why recent methods, such as diffusion and flow matching…

Machine Learning · Computer Science 2025-12-03 Quentin Bertrand , Anne Gagneux , Mathurin Massias , Rémi Emonet

In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common…

Machine Learning · Computer Science 2021-09-27 Aviv Tamar , Daniel Soudry , Ev Zisselman

In this paper (part 1), we describe a derivative-free trust-region method for solving unconstrained optimization problems. We will discuss a method when we relax the model order assumption and use artificial neural network techniques to…

Optimization and Control · Mathematics 2020-05-26 Mostafa Rezapour , Thomas Asaki

Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupling and autoregressive transformations to lift up invertible…

Machine Learning · Computer Science 2021-02-15 Antoine Wehenkel , Gilles Louppe

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

Machine Learning · Statistics 2023-01-06 Chengchun Shi , Zhengling Qi , Jianing Wang , Fan Zhou

The issue of fairness in machine learning stems from the fact that historical data often displays biases against specific groups of people which have been underprivileged in the recent past, or still are. In this context, one of the…

Machine Learning · Computer Science 2022-01-19 Mattia Cerrato , Marius Köppel , Alexander Segner , Stefan Kramer

Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Justin Fu , Marvin Zhang , Sergey Levine

Real-world optimization problems often involve complex objective functions with costly evaluations. While Bayesian optimization (BO) with Gaussian processes is effective for these challenges, it suffers in high-dimensional spaces due to…

Machine Learning · Computer Science 2024-12-17 Nobuo Namura , Sho Takemori

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly…

Machine Learning · Computer Science 2026-05-27 Yu Luo , Shuo Han , Yihan Hu , Lei Lv , Huaping Liu , Fuchun Sun , Jianye Hao , Dong Li

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Dmitrii Marin , Yuri Boykov

In this paper, we present convergence guarantees for a modified trust-region method designed for minimizing objective functions whose value and gradient and Hessian estimates are computed with noise. These estimates are produced by generic…

Optimization and Control · Mathematics 2023-07-04 Liyuan Cao , Albert S. Berahas , Katya Scheinberg

Among on-policy reinforcement learning algorithms, Proximal Policy Optimization (PPO) demonstrates is widely favored for its simplicity, numerical stability, and strong empirical performance. Standard PPO relies on surrogate objectives…

Machine Learning · Computer Science 2026-02-03 Shunpeng Yang , Ben Liu , Hua Chen

Through examples of coordinate and probability transformation between different distributions, the basic principle of normalizing flow is introduced in a simple and concise manner. From the perspective of the distribution of random variable…

Machine Learning · Computer Science 2024-01-22 Hongjun Zhang

Researchers have demonstrated that Deep Reinforcement Learning (DRL) is a powerful tool for finding policies that perform well on complex robotic systems. However, these policies are often unpredictable and can induce highly variable…

Robotics · Computer Science 2022-03-08 Sean Gillen , Asutay Ozmen , Katie Byl

Normalising Flows are non-parametric statistical models characterised by their dual capabilities of density estimation and generation. This duality requires an inherently invertible architecture. However, the requirement of invertibility…

Machine Learning · Statistics 2024-06-28 Eshant English , Matthias Kirchler , Christoph Lippert

The present study presents a novel application for normalizing flows for domain adaptation. The study investigates the ability of flow based neural networks to improve signal extraction of $\Lambda$ Hyperons at CLAS12. Normalizing Flows can…

High Energy Physics - Experiment · Physics 2024-03-22 Rowan Kelleher , Matthew McEneaney , Anselm Vossen

Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle…

Artificial Intelligence · Computer Science 2021-11-11 Xiongjie Chen , Hao Wen , Yunpeng Li

Policy learning can be used to extract individualized treatment regimes from observational data in healthcare, civics, e-commerce, and beyond. One big hurdle to policy learning is a commonplace lack of overlap in the data for different…

Machine Learning · Statistics 2020-12-04 Nathan Kallus

Standard trust-region methods constrain policy updates via Kullback-Leibler (KL) divergence. However, KL controls only an average divergence and does not directly prevent rare, large likelihood-ratio excursions that destabilize…

Machine Learning · Computer Science 2026-02-09 Gaurish Trivedi , Alakh Sharma , Kartikey Singh Bhandari , Yash Sinha , Pratik Narang , Dhruv Kumar , Jagat Sesh Challa
‹ Prev 1 8 9 10 Next ›