reinforcement learning

Control-theoretic methods for reinforcement learning

Reinforcement Learning (RL) has become a cornerstone of modern artificial intelligence and control theory, enabling complex decision-making tasks in a wide variety of domains such as robotics, autonomous driving and strategic games. While deep neural networks allow RL methods to address large-scale problems, exploiting...

Motion Planning in Urban Environments via Self-Play Reinforcement Learning

International audience

AI-Assisted Self-Powered Flexible Electronic System for Energy Management

This review systematically examines recent progress in AI-enabled energy management strategies for self-powered flexible electronic systems and categorizes AI integration across three key dimensions: at the algorithmic level, predictive models and reinforcement learning enable dynamic power allocation and coordinate mu...

Reward expectation signals in the superior colliculus during associative learning

Predicting future rewards allows neutral sensory cues to acquire motivational significance and guide goal-directed actions that maximise reward acquisition1. These reward predictions are updated when outcomes differ from expectations resulting in an error in prediction2. Midbrain dopamine neurons provide a canonical ne...

Multi-agent joint optimization reinforcement learning algorithm based on impedance matching space segmentation

Reinforcement learning with control-barrier-function safety filters for trajectory tracking on a Stewart platform: campaign v3

Code, aggregated data and provenance for the simulation campaign behind the manuscript. Twelve training seeds, twenty-five evaluation episodes per seed on a fixed shared evaluation base, four arms. Raw policy checkpoints and TensorBoard logs are not included: they exceed two gigabytes and every reported number is deriv...

Positive Teaching and School Wellbeing among Students

The present study explores the role of positive teaching practices in promoting school wellbeing among students using a qualitative research approach. Guided by principles of positive psychology, the study aimed to understand students’ lived experiences of supportive teaching behaviors and their influence on emotional,...

Bayesian Deep Reinforcement Learning for Autonomous Driving with Uncertain Pedestrian Intent

Research on Safe Decision-Making for Highway Scenario Autonomous Driving Based on Deep Reinforcement Learning

Improved Deep Reinforcement Learning Approach for Lane-Level Variable Speed Limit Control of Mixed Traffic Flow

Fábrica de Modelos — herramienta IA para la academia (UMH)

Recorrido interactivo por las siete etapas de construcción de un modelo de lenguaje —tokenización BPE, atención, preentrenamiento, ajuste a instrucciones, refuerzo e inferencia— con un Transformer que se entrena de verdad en JavaScript dentro de la propia página, sin instalar nada. Material didáctico construido sobre e...

MulTADrug-GPT: A sample-efficient generative framework for multi-target drug design via reinforcement and preference learning

This repository contains the code, data, and pre-trained models for "MulTADrug-GPT: A sample-efficient generative framework for multi-target drug design via reinforcement and preference learning". For detailed instructions on environment setup and the step-by-step execution of the training and evaluation pipelines, ple...