English
Related papers

Related papers: Collective Sampling: An Ex Ante Perspective

200 papers

Ensemble methods have been widely applied in Reinforcement Learning (RL) in order to enhance stability, increase convergence speed, and improve exploration. These methods typically work by employing an aggregation mechanism over actions of…

Artificial Intelligence · Computer Science 2019-10-09 Rishav Chourasia , Adish Singla

The objective of this paper is to initiate a qualitative analysis of dynamic flow in traffic networks by using the competitive equilibrium model of multiple market systems. A network is modeled as a dynamic graph where routes (edges) are…

Systems and Control · Computer Science 2017-11-30 Dragoslav D. Šiljak

In this work we introduce an approach for modeling and analyzing collective behavior of a group of agents using moments. We represent the group of agents via their distribution and derive a method to estimate the dynamics of the moments. We…

Optimization and Control · Mathematics 2020-04-30 Silun Zhang , Axel Ringh , Xiaoming Hu , Johan Karlsson

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Machine Learning · Computer Science 2022-12-12 Yiding Jiang , Evan Zheran Liu , Benjamin Eysenbach , Zico Kolter , Chelsea Finn

We study efficiency in general collective choice problems where agents have ordinal preferences and randomization is allowed. We explore the structure of preference profiles where ex-ante and ex-post efficiency coincide, offer a unifying…

Theoretical Economics · Economics 2022-08-22 Federico Echenique , Joseph Root , Fedor Sandomirskiy

Federated learning offers a decentralized approach to machine learning, where multiple agents collaboratively train a model while preserving data privacy. In this paper, we investigate the decision-making and equilibrium behavior in…

Computer Science and Game Theory · Computer Science 2025-03-13 Lihui Yi , Xiaochun Niu , Ermin Wei

In many predictive contexts (e.g., credit lending), true outcomes are only observed for samples that were positively classified in the past. These past observations, in turn, form training datasets for classifiers that make future…

Machine Learning · Computer Science 2024-06-04 Vijay Keswani , Anay Mehrotra , L. Elisa Celis

Social animals have to make collective decisions on a daily basis. In most instances, these decisions are taken by consensus, when the group does what the majority of individuals want. Individuals have to base these decisions on the…

Populations and Evolution · Quantitative Biology 2013-08-06 David Lusseau

Unsupervised ensemble learning emerged to address the challenge of combining multiple learners' predictions without access to ground truth labels or additional data. This paradigm is crucial in scenarios where evaluating individual…

Machine Learning · Computer Science 2026-01-29 Ariel Maymon , Yanir Buznah , Uri Shaham

Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment settings the test environment's transitions differ from training, and classical offline…

Machine Learning · Computer Science 2026-05-19 Surbhi Goel , Jonathan Pei , James Wang

Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to the reference summary.…

Computation and Language · Computer Science 2022-04-01 Yixin Liu , Pengfei Liu , Dragomir Radev , Graham Neubig

We construct subgame-perfect equilibria with mixed strategies for symmetric stochastic timing games with arbitrary strategic incentives. The strategies are qualitatively different for local first- or second-mover advantages, which we…

Optimization and Control · Mathematics 2018-05-23 Jan-Henrik Steg

For three natural classes of dynamic decision problems; 1. additively separable problems, 2. discounted problems, and 3. discounted problems for a fixed discount factor; we provide necessary and sufficient conditions for one sequential…

Theoretical Economics · Economics 2024-05-24 Mark Whitmeyer , Cole Williams

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…

In this paper, we investigate the effectiveness of contrastive learning methods for predicting grasp outcomes in an unsupervised manner. By utilizing a publicly available dataset, we demonstrate that contrastive learning methods perform…

Robotics · Computer Science 2023-09-22 Chengliang Liu , Binhua Huang , Yiwen Liu , Yuanzhe Su , Ke Mai , Yupo Zhang , Zhengkun Yi , Xinyu Wu

We compare how well agents aggregate information in two repeated social learning environments. In the first setting agents have access to a public data set. In the second they have access to the same data, and also to the past actions of…

Theoretical Economics · Economics 2026-05-20 Marina Agranov , Gabriel Lopez-Moctezuma , Philipp Strack , Omer Tamuz

Inspired by e-participation systems, in this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes drawbacks of existing approaches by allowing users to…

Artificial Intelligence · Computer Science 2020-07-15 Jordi Ganzer , Natalia Criado , Maite Lopez-Sanchez , Simon Parsons , Juan A. Rodriguez-Aguilar

Judgment aggregation problems form a class of collective decision-making problems represented in an abstract way, subsuming some well known problems such as voting. A collective decision can be reached in many ways, but a direct one-step…

Artificial Intelligence · Computer Science 2016-08-30 Marija Slavkovik , Wojciech Jamroga

We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…

Artificial Intelligence · Computer Science 2021-05-21 Siqi Liu , Guy Lever , Josh Merel , Saran Tunyasuvunakool , Nicolas Heess , Thore Graepel

In this work we study the knowledge acquisition process in a teaching-learning scenario that takes place within the classroom. We explore two complementary approaches, which include classroom observations and student surveys, and the…

Physics Education · Physics 2021-03-15 Fátima Velásquez-Rojas , María Fabiana Laguna
‹ Prev 1 8 9 10 Next ›