Publications associées à Optimal Combination Policies For Adaptive Social Learning

Publications associées (47)

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

EPFL2025

Domain shift, domain adaptation, and generalization: A focus on MRI

Tobias Kober, Meritxell Bach Cuadra, Veronica Lily Ravano, Jonas Richiardi

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Academic Press2025

Learning to Assemble with Alternative Plans

Gabriel Rémi Vallat, Maryam Kamgarpour, Stefana Parascho, Ziqi Wang, Jingwen Wang

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

Association for Computing Machinery (ACM)2025

Endogenous Energy Efficiency Improvement in Housing and Cement Sectors in Switzerland

Sergey Arzoyan

The reduction of energy consumption in the residential building stock and cement industry is a substantial component of the Swiss Energy Strategy 2050. Therefore, it is vital to identify the potential for EEI in these two sectors. In this study, a new meth ...

EPFL2023

Predicting party switching through machine learning and open data

Silvestro Micera

Parliament dynamics might seem erratic at times. Predicting future voting patterns could support policy design based on the simulation of voting scenarios. The availability of open data on legislative activities and machine learning tools might enable such ...

CELL PRESS2023

Frihet, sikkerhet, forstaden: Brev fra Amerika

Nagy Makhlouf

Why have countries formerly leading public policies of housing – Norway, the U.K., France, etc. – shifted towards privatizing accommodation from the late 1970s? Have these States merely let go of housing and handed it over to private interests in the name ...

2024

The Economics of Incomplete Plan - on Conditions, Procedures and Design of Future Mission - Oriented Innovation Policies

Dominique Foray

The buzzword in industrial policy and innovation policy circles is mission-oriented innovation policy (MOIP) -which means a policy to encourage innovation intended to accomplish a certain missionwhether it be a societal challenge (climate change, global he ...

INST ESTUDIOS FISCALES2022

Designing the Future Workforce through STEAM Education

Laura Filippa Ferrarello

Learning in interdisciplinary spaces is key for generating new models of thinking (Aboelela et al., 2007, p. 341 in Tobi & Kampen, 2018); interdisciplinary thinking nurtures creativity and a critical enquiry of social challenges thanks to the entanglement ...

Routledge2024

Optimal recovery of unsecured debt via interpretable reinforcement learning

Thomas Alois Weber, Michael Mark

This paper addresses the issue of interpretability and auditability of reinforcement-learning agents employed in the recovery of unsecured consumer debt. To this end, we develop a deterministic policy-gradient method that allows for a natural integration o ...

2022

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

Andréa Serge Alfredo Miele, Daniil Pyatko, Caglar Gulcehre, Skander Moalla

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting n ...

2024

From Marshall Plan to “Hilton in the wild”: The Transnational History of a Cooperative Housing Block in Esat, Ankara

Sila Karatas

This paper concerns the planning, design, and construction history of a postwar multifamily housing block in Ankara, Turkey, viewed from the perspective of the transnational and local networks behind its realization. Built by the Mintrak Building Cooperati ...

2022

Kernels, data & physics

Francesco Cagnetta

Lecture notes from the course given by Professor Julia Kempe at the summer school ‘Statistical physics of Machine Learning’ in Les Houches. The notes discuss the so-called NTK approach to problems in machine learning, which consists of gaining an understan ...

2024

The Rebound Effects from Industrial Energy Efficiency Improvements

Michel Zimmermann

In energy policy, energy efficiency constitutes a central element in reducing domestic and, specifically, industrial en-ergy use. Unfortunately, the effectiveness of energy efficiency improvements in achieving its targets is known to be limited by rebound ...

EPFL2022

Robust Machine Learning - Distributed Methods for Safe AI

Rachid Guerraoui, Nirupam Gupta, Rafaël Benjamin Pinot

Today, machine learning algorithms are often distributed across multiple machines to leverage more computing power and more data. However, the use of a distributed framework entails a variety of security threats. In particular, some of the machines may mis ...

Springer2024

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Lakmal Buddika Meegahapola

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

EPFL2024

Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates

Ali H. Sayed, Kun Yuan, Lucas Cesar Eduardo Cassano

This article develops a fully decentralized multiagent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered by following different behav ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Engineering novel protein interactions with therapeutic potential using deep learning-guided surface design

Anthony Marchand

Proteins are foundational biomolecules of life playing a crucial role in a myriad of biological processes. Their function often requires interplay with other biomolecules, including proteins themselves. Protein-protein interactions (PPIs) are essential for ...

EPFL2024

Logical Team Q-learning: An approach towards factored policies in cooperative MARL

Ali H. Sayed, Lucas Cesar Eduardo Cassano

We address the challenge of learning factored policies in cooperative MARL scenarios. In particular, we consider the situation in which a team of agents collaborates to optimize a common cost. The goal is to obtain factored policies that determine the indi ...

MICROTOME PUBLISHING2021

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

Alireza Modirshanechi

Human babies have a natural desire to interact with new toys and objects, through which they learn how the world around them works, e.g., that glass shatters when dropped, but a rubber ball does not. When their predictions are proven incorrect, such as whe ...

EPFL2024

Exploring policy change through agent-based simulation

Raphaël Klein

Policymaking is a complex process that has been studied using policy process theories almost exclusively. These theories have been built using a large number of qualitative cases. Such methods are useful for theory building but remain limited for theory ex ...

EPFL2021