English
Related papers

Related papers: Exploring validation metrics for offline model-bas…

200 papers

Many real-world scientific and industrial applications require the optimization of expensive black-box functions. Bayesian Optimization (BO) provides an effective framework for such problems. However, traditional BO methods are prone to get…

Artificial Intelligence · Computer Science 2025-09-29 Zhuo Yang , Daolang Wang , Lingli Ge , Beilun Wang , Tianfan Fu , Yuqiang Li

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…

Machine Learning · Computer Science 2021-02-15 Ron Dorfman , Idan Shenfeld , Aviv Tamar

Virtual cell (VC) models aim to predict cellular responses to any perturbations in silico and have emerged as a promising approach for drug discovery and precision medicine. Yet, a clear gap still remains: while models routinely reported…

Cell Behavior · Quantitative Biology 2026-05-01 Xinjie Mao , Songming Zhang , Qianhong Wen , Xiangyu Wen , Kedu Jin , Hao Wu , Shuizhou Chen , Yuqiang Li , Lei Bai , Qi Liu , Ning Ding , Siqi Sun , Zhangyang Gao

Molecular property optimization (MPO) problems are inherently challenging since they are formulated over discrete, unstructured spaces and the labeling process involves expensive simulations or experiments, which fundamentally limits the…

Biomolecules · Quantitative Biology 2024-01-04 Farshud Sorourifar , Thomas Banker , Joel A. Paulson

Rule-based classification models described in the language of logic directly predict boolean values, rather than modeling a probability and translating it into a prediction as done in statistical models. The vast majority of existing…

Artificial Intelligence · Computer Science 2022-11-04 Yusik Kim

This paper uncovers and explores the close relationship between Monte Carlo Optimization of a parametrized integral (MCO), Parametric machine-Learning (PL), and `blackbox' or `oracle'-based optimization (BO). We make four contributions.…

Machine Learning · Computer Science 2011-11-09 David H. Wolpert , Dev G. Rajnarayan

Recently, Meta-Black-Box Optimization with Reinforcement Learning (MetaBBO-RL) has showcased the power of leveraging RL at the meta-level to mitigate manual fine-tuning of low-level black-box optimizers. However, this field is hindered by…

Machine Learning · Computer Science 2023-10-30 Zeyuan Ma , Hongshu Guo , Jiacheng Chen , Zhenrui Li , Guojun Peng , Yue-Jiao Gong , Yining Ma , Zhiguang Cao

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Machine Learning · Computer Science 2025-05-20 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Dongha Lee , Jinyoung Yeo

Solid evaluation of neural machine translation (NMT) is key to its understanding and improvement. Current evaluation of an NMT system is usually built upon a heuristic decoding algorithm (e.g., beam search) and an evaluation metric…

Computation and Language · Computer Science 2022-10-11 Jianhao Yan , Chenming Wu , Fandong Meng , Jie Zhou

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee

Markov Decision Problems (MDPs) provide a foundational framework for modelling sequential decision-making across diverse domains, guided by optimality criteria such as discounted and average rewards. However, these criteria have inherent…

Artificial Intelligence · Computer Science 2025-08-26 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent…

Machine Learning · Computer Science 2024-04-09 Ran Wei , Nathan Lambert , Anthony McDonald , Alfredo Garcia , Roberto Calandra

An algorithmic decision-maker incentivizes people to act in certain ways to receive better decisions. These incentives can dramatically influence subjects' behaviors and lives, and it is important that both decision-makers and…

Machine Learning · Computer Science 2019-10-15 Yonadav Shavit , William S. Moses

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this…

Machine Learning · Computer Science 2026-04-17 Xiaoyi Dong , Xi Sheryl Zhang , Jian Cheng

The evaluation of recommender system fairness has become increasingly important, especially with recent legislation that emphasises the development of fair and responsible artificial intelligence. This has led to the emergence of various…

Information Retrieval · Computer Science 2026-04-29 Theresia Veronika Rampisela

Optimisation algorithms are commonly compared on benchmarks to get insight into performance differences. However, it is not clear how closely benchmarks match the properties of real-world problems because these properties are largely…

Neural and Evolutionary Computing · Computer Science 2021-07-15 Koen van der Blom , Timo M. Deist , Vanessa Volz , Mariapia Marchi , Yusuke Nojima , Boris Naujoks , Akira Oyama , Tea Tušar

In real-world problems, uncertainties (e.g., errors in the measurement, precision errors) often lead to poor performance of numerical algorithms when not explicitly taken into account. This is also the case for control problems, where…

Optimization and Control · Mathematics 2020-12-18 Carlos Ignacio Hernández Castellanos , Sina Ober-Blöbaum , Sebastian Peitz

Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two main approaches have emerged: the forward approach, which learns a mapping from input to its value,…

Machine Learning · Computer Science 2025-01-03 Can Sam Chen , Christopher Beckham , Zixuan Liu , Xue Liu , Christopher Pal

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…

Machine Learning · Computer Science 2024-04-11 Guojian Wang , Faguo Wu , Xiao Zhang

Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability to learn offline is particularly important in many…

‹ Prev 1 8 9 10 Next ›