Concept

Renforcement

Publications associées (127)

Motion capture and reinforcement learning of dynamically stable humanoid movement primitives

Direct transfer of human motion trajectories to humanoid robots does not result in dynamically stable robot movements due to the differences in human and humanoid robot kinematics and dynamics. We developed a system that converts human movements captured b ...

IEEE2013

City size, network structure and traffic congestion

Nikolaos Geroliminis

This paper presents an alternative approach for analyzing the relationship between land use and traffic congestion by employing the Macroscopic Fundamental Diagram (MFD). The MFD is an empirically observed relationship between traffic flow and traffic dens ...

Elsevier2013

Towards an activity-based model for pedestrian facilities

Michel Bierlaire, Bilal Farooq, Antonin Danalet

This paper develops a framework for understanding pedestrian mobility pattern from WiFi traces and other data sources. It can be used to forecast demand for pedestrian facilities such as railway stations, music festivals, campus, airports, supermarkets or ...

2013

The temporal dynamics of feature integration for color and form

Michael Herzog

When two visual stimuli are presented in rapid succession only one fused image is perceived. For example, a red disk followed by a green disk is perceived as a single yellow disk (e.g., Efron, Perc Psychophys, 1973). For two verniers that last 30ms each, i ...

Association for Research in Vision and Ophthalmology2012

Automatic Skill Acquisition in Reinforcement Learning Using Graph Centrality Measures

Martin Hasler, Ali Ajdari Rad, Alireza Khadivi

Mechanisms on automatic discovery of macro actions or skills in reinforcement learning methods are mainly focused on subgoal discovery methods. Among the proposed algorithms, those based on graph centrality measures demonstrate a high performance gain. In ...

2012

Applications of bent-up bars as shear and integrity reinforcement in R/C slabs

Aurelio Muttoni, Miguel Fernández Ruiz, Stefan Lips, Luca Tassinari

Bent-up bars were extensively used as shear reinforcement in beams and slabs from the first R/C developments up to the 1970’s. Their use was justified by the fact that they allowed enhanced development of the tensile reinforcement at the same time they act ...

fib Symposium Prague 20112011

Separate encoding of model-based and model-free valuations in the human brain

Behavioral studies have long shown that humans solve problems in two ways, one intuitive and fast (System 1, model-free), and the other reflective and slow (System 2, model-based). The neurobiological basis of dual process problem solving remains unknown d ...

Elsevier2011

Act Quickly, Decide Later: Long-latency Visual Processing Underlies Perceptual Decisions but Not Reflexive Behavior

Humans largely guide their behavior by their visual representation of the world. Recent studies have shown that visual information can trigger behavior within 150 msec, suggesting that visually guided responses to external events, in fact, precede consciou ...

2011

The effects of practice schedule on learning a complex judgment task

The effects of practice schedule on learning a complex judgment task were investigated. In Experiment 1, participants' judgment accuracy on a retention test was higher after a random practice schedule than after a blocked schedule or operational schedule. ...

2011

Perceptual Learning, Roving and the Unsupervised Bias

Michael Herzog, Wulfram Gerstner, Aaron Michael Clarke

Perceptual learning is reward-based. A recent mathematical analysis showed that any reward-based learning system can learn two tasks only when the mean reward is identical for both tasks [Frémaux, Sprekeler and Gerstner, 2010, The Journal of Neuroscience, ...

2011

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