Publications associées à Renforcement

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

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

Non-invasive stimulation of the human striatum disrupts reinforcement learning of motor skills

Friedhelm Christoph Hummel, Takuya Morishita, Pierre Theopistos Vassiliadis, Elena Beanato, Esra Neufeld, Fabienne Windel, Maximilian Jonas Wessel, Traian Popa, Julie Duqué

Reinforcement feedback can improve motor learning, but the underlying brain mechanisms remain underexplored. In particular, the causal contribution of specific patterns of oscillatory activity within the human striatum is unknown. To address this question, ...

Nature Portfolio2024

Unveiling the complexity of learning and decision-making

Wei-Hsiang Lin

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...

EPFL2024

Simulating intra-household interactions for in- and out-of-home activity scheduling

Michel Bierlaire, Timothy Michael Hillel, Negar Rezvany

Various interactions, time arrangements, and constraints exist for individuals scheduling their day as a member of a household, which affect their in-home as well as out-of-home activity schedule. However, the existing activity-based models are mostly base ...

Pergamon-Elsevier Science Ltd2023

Mechanisms underlying reinforcement learning of motor skills

Pierre Theopistos Vassiliadis

Motor learning allows animals, including human beings, to acquire skills that are es-sential for efficient interactions with the environment. This ability to learn new motor skills is of great practical relevance for daily-life activities (such as when lea ...

EPFL2023

Dynamic indoor thermal environment using Reinforcement Learning-based controls: Opportunities and challenges

Dolaana Khovalyg, Arnab Chatterjee

Currently, the indoor thermal environment in many buildings is controlled by conventional control techniques that maintain the indoor temperature within a prescribed deadband. The latest research provides evidence that more dynamic variations of the indoor ...

2023

On the role of energy infrastructure in the energy transition. Case study of an energy independent and CO2 neutral energy system for Switzerland

François Maréchal, Jonas Schnidrig, Sidi-Rachid Cherkaoui, Manuele Domenico Margni

The transition towards renewable energy is leading to an important strain on the energy grids. The question of designing and deploying renewable energy technologies in symbiosis with existing grids and infrastructure is arising. While current energy system ...

2023

Reinforcement learning approach to control an inverted pendulum: A general framework for educational purposes

Jesus Sanchez Rodriguez

Machine learning is often cited as a new paradigm in control theory, but is also often viewed as empirical and less intuitive for students than classical model-based methods. This is particularly the case for reinforcement learning, an approach that does n ...

PUBLIC LIBRARY SCIENCE2023

A striatal circuit balances learned fear in the presence and absence of sensory cues

Ralf Schneggenburger, Olexiy Kochubey, Michael Kintscher

During fear learning, defensive behaviors like freezing need to be finely balanced in the presence or absence of threat-predicting cues (conditioned stimulus, CS). Nevertheless, the circuits underlying such balancing are largely unknown. Here, we investiga ...

eLIFE SCIENCES PUBL LTD2023

Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules

Colin Neil Jones, Loris Di Natale, Bratislav Svetozarevic

Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert knowledge of the syste ...

2023