Concept

Renforcement

Publications associées (127)

Surprise-based model estimation in reinforcement learning: algorithms and brain signatures

Learning how to act and adapting to unexpected changes are remarkable capabilities of humans and other animals. In the absence of a direct recipe to follow in life, behaviour is often guided by rewarding and by surprising events. A positive or a negative o ...

EPFL2021

Investigating the effects of pre-stimulus activity on spatio-temporal feature integration

Michael Herzog, David Pascucci, Maëlan Quentin Menétrey

Pre-stimulus brain activity is thought to modulate visual perception. However, the underlying processes are strongly debated. Moreover, the role of pre-stimulus activity beyond tasks with single, simple stimuli is largely unknown. Here, we analyzed electro ...

2021

A Reinforcement Learning Approach to Train Routing and Scheduling

Zora Oswald

Good train scheduling for a big network with many trains is very hard to achieve. As the trains are competing for the tracks with one another, the number of constraints grows rapidly. Trying to take advantage of emerging technologies in the areas of optimi ...

2020

Neural Correlates of Reinforcement Learning: eligibility trace, reward prediction error, novelty and surprise

He Xu

In reinforcement learning (RL), an agent makes sequential decisions to maximise the reward it can obtain from an environment. During learning, the actual and expected outcomes are compared to tell whether a decision was good or bad. The difference between ...

EPFL2020

Adaptive Laser Welding Control: A Reinforcement Learning Approach

Silvio Zanoli, Giulio Masinelli

Despite extensive research efforts in the field of laser welding, the imperfect repeatability of the weld quality still represents an open topic. Indeed, the inherent complexity of the underlying physical phenomena prevents the implementation of an effecti ...

2020

DISK: learning local features with policy gradient

Pascal Fua, Eduard Trulls Fortuny, Michal Jan Tyszkiewicz

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveragin ...

2020

Risk prediction error signaling: A two-component response?

Michael Herzog, Ophélie Gladys Favrod, Kerstin Preuschoff, Marc Michael Lauffs, Sophie Alberta Catherine Geoghan

Organisms use rewards to navigate and adapt to (uncertain) environments. Error-based learning about rewards issupported by the dopaminergic system, which is thought to signal reward prediction errors to make adjustmentsto past predictions. More recently, t ...

2020

Data-driven methods for building control - A review and promising future directions

Colin Neil Jones, Yingzhao Lian, Emilio Maddalena

A review of the heating, ventilation and air-conditioning control problem for buildings is presented with particular emphasis on its distinguishing features. Next, we not only examine how data-driven algorithms have been exploited to tackle the main challe ...

PERGAMON-ELSEVIER SCIENCE LTD2020

One-shot learning and behavioral eligibility traces in sequential decision making

Michael Herzog, Wulfram Gerstner, Kerstin Preuschoff, Marco Philipp Lehmann, He Xu, Vasiliki Liakoni

In many daily tasks, we make multiple decisions before reaching a goal. In order to learn such sequences of decisions, a mechanism to link earlier actions to later reward is necessary. Reinforcement learning (RL) theory suggests two classes of algorithms s ...

2019

Combined Rehabilitation Promotes the Recovery of Structural and Functional Features of Healthy Neuronal Networks after Stroke

Silvestro Micera, Stefano Lai, Francesco Saverio Pavone

Rehabilitation is considered the most effective treatment for promoting the recovery of motor deficits after stroke. One of the most challenging experimental goals is to unambiguously link brain rewiring to motor improvement prompted by rehabilitative ther ...

2019

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search