English
Related papers

Related papers: Boosting Trust Region Policy Optimization by Norma…

200 papers

We propose a novel trust region method for solving a class of nonsmooth, nonconvex composite-type optimization problems. The approach embeds inexact semismooth Newton steps for finding zeros of a normal map-based stationarity measure for…

Optimization and Control · Mathematics 2023-10-04 Wenqing Ouyang , Andre Milzarek

Some real-world decision-making problems require making probabilistic forecasts over multiple steps at once. However, methods for probabilistic forecasting may fail to capture correlations in the underlying time-series that exist over long…

Machine Learning · Computer Science 2022-01-19 Arec Jamgochian , Di Wu , Kunal Menda , Soyeon Jung , Mykel J. Kochenderfer

In this paper we consider the use of probabilistic or random models within a classical trust-region framework for optimization of deterministic smooth general nonlinear functions. Our method and setting differs from many stochastic…

Optimization and Control · Mathematics 2013-04-11 Afonso S. Bandeira , Katya Scheinberg , Luis Nunes Vicente

A trust-region algorithm is presented for finding approximate minimizers of smooth unconstrained functions whose values and derivatives are subject to random noise. It is shown that, under suitable probabilistic assumptions, the new method…

Optimization and Control · Mathematics 2022-01-03 S. Bellavia , G. Gurioli , B. Morini , Ph. L. Toint

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust…

Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…

Machine Learning · Computer Science 2026-02-02 Christiaan P. Opperman , Anna S. Bosman , Katherine M. Malan

Recommender systems predict what items a user will interact with next, based on their past interactions. The problem is often approached through supervised learning, but recent advancements have shifted towards policy optimization of…

Machine Learning · Computer Science 2023-04-28 Dawen Liang , Nikos Vlassis

A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an ``optimal'' predicted outcome distribution according to some…

Econometrics · Economics 2025-05-29 Anders Bredahl Kock , David Preinerstorfer

Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$. However, modern LLM-RL pipelines suffer from unavoidable…

Machine Learning · Computer Science 2026-03-02 Yingru Li , Jiacai Liu , Jiawei Xu , Yuxuan Tong , Ziniu Li , Qian Liu , Baoxiang Wang

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by…

Machine Learning · Computer Science 2019-04-29 Robert Pinsler , Peter Karkus , Andras Kupcsik , David Hsu , Wee Sun Lee

We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon:…

Machine Learning · Computer Science 2025-01-29 Vivek Myers , Catherine Ji , Benjamin Eysenbach

The data preprocessing stage is crucial in clustering. Features may describe entities using different scales. To rectify this, one usually applies feature normalisation aiming at rescaling features so that none of them overpowers the others…

Machine Learning · Computer Science 2021-04-26 Renato Cordeiro de Amorim , Vladimir Makarenkov

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian…

Machine Learning · Computer Science 2025-01-07 Xiongjie Chen , Yunpeng Li

In convolutional neural networks (CNNs), pooling operations play important roles such as dimensionality reduction and deformation compensation. In general, max pooling, which is the most widely used operation for local pooling, is performed…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Takato Otsuzuki , Hideaki Hayashi , Yuchen Zheng , Seiichi Uchida

Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods. In this paper, we present a simplified…

Machine Learning · Computer Science 2020-08-10 Armen Aghajanyan , Akshat Shrivastava , Anchit Gupta , Naman Goyal , Luke Zettlemoyer , Sonal Gupta

Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which…

Machine Learning · Computer Science 2026-04-02 Ruijie Hao , Longfei Zhang , Yang Dai , Yang Ma , Xingxing Liang , Guangquan Cheng

Biologically inspired, from the early HMAX model to Spatial Pyramid Matching, pooling has played an important role in visual recognition pipelines. Spatial pooling, by grouping of local codes, equips these methods with a certain degree of…

Computer Vision and Pattern Recognition · Computer Science 2015-05-06 Mateusz Malinowski , Mario Fritz

We present a computational framework for efficient learning, sampling, and distribution of general Bayesian posterior distributions. The framework leverages a machine learning approach for the construction of normalizing flows for the…

Nuclear Theory · Physics 2023-10-10 Yukari Yamauchi , Landon Buskirk , Pablo Giuliani , Kyle Godbey

As we enter the UN Decade on Ecosystem Restoration, creating effective incentive structures for forest and landscape restoration has never been more critical. Policy analysis is necessary for policymakers to understand the actors and rules…

Computation and Language · Computer Science 2022-01-19 Jordi Planas , Daniel Firebanks-Quevedo , Galina Naydenova , Ramansh Sharma , Cristina Taylor , Kathleen Buckingham , Rong Fang

Modern policy optimization methods roughly follow the policy mirror descent (PMD) algorithmic template, for which there are by now numerous theoretical convergence results. However, most of these either target tabular environments, or can…

Machine Learning · Computer Science 2025-07-08 Uri Sherman , Tomer Koren , Yishay Mansour