reinforcement learning

Ray-Traced D2D Link Scheduling: Dataset, Code and Results for "Graph Neural Networks for D2D Link Scheduling: Centralized and Distributed Schedulers Evaluated with Sionna Ray-Traced Channels"

Supporting dataset, source code, trained models and result files for the manuscript "Graph Neural Networks for D2D Link Scheduling: Centralized and Distributed Schedulers Evaluated with Sionna Ray-Traced Channels" (Sensors, MDPI; revised version). The archive contains 24,000 device-to-device network snapshots generated...

Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation with xTB-Verified Reinforcement Learning

Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation with xTB-Verified Reinforcement Learning at https://arxiv.org/abs/2607.15918 source: https://github.com/tkotani/ADT (release v2.1) Dataset to reproduce the data in the paper.v2.1: the RLVR generator is rlvr_E240direct.pt (it replaces paper_rlvl.ckpt...

A comparative study of evolutionary algorithms and activation functions in neuroevolution deep reinforcement learning

Four evolutionary optimization algorithms and six activation functions are investigated, resulting in 24 different configurations, and their performance on the Inverted Double Pendulum environment is evaluated, where one algorithm consistently exhibits stable learning across most activation functions.

DP-PreCo-GRL: code, data and raw results for 'Preference-conditioned graph reinforcement learning for energy-aware flexible job-shop scheduling: a critical evaluation'

Simulator, baselines (dispatching rules, PWG, NSGA-II/III), preference-conditioned graph policy, PPO trainer, analysis scripts, trained checkpoints and per-run objective vectors of the manuscript.

The Price of a Degree-Hour in Data-Centre Cooling: Auditing Deep Reinforcement Learning against Model Predictive Control - data and analysis release

Derived results and analysis code for the article "The Price of a Degree-Hour in Data-Centre Cooling: Auditing Deep Reinforcement Learning against Model Predictive Control", submitted to Energy and AI. The deposit contains every derived quantity behind the article's tables and figures: per-episode held-out evaluation r...

The Price of a Degree-Hour in Data-Centre Cooling: Auditing Deep Reinforcement Learning against Model Predictive Control - data and analysis release

Derived results and analysis code for the article "The Price of a Degree-Hour in Data-Centre Cooling: Auditing Deep Reinforcement Learning against Model Predictive Control", submitted to Energy and AI. The deposit contains every derived quantity behind the article's tables and figures: per-episode held-out evaluation r...

The Golden Triangle in Human-Machine Interaction: Deep Learning, Reinforcement Learning, and Natural Language Processing – A Survey

DP-PreCo-GRL: code, data and raw results for 'Preference-conditioned graph reinforcement learning for energy-aware flexible job-shop scheduling: a critical evaluation'

Simulator, baselines (dispatching rules, PWG, NSGA-II/III), preference-conditioned graph policy, PPO trainer, analysis scripts, trained checkpoints and per-run objective vectors of the manuscript.

The Effect of Educational Exercises Based on the Gamification Strategy on Developing Selected Physical Fitness Components Among Male Students

Examining the efficacy of gamification-based instructional exercises in enhancing certain motor skills specifically , agility, dynamic balance , coordination and transitional speed among College of Physical Education and Sports Sciences students was the primary objective of this research . The purpose of the study was...

Laying the groundwork

Before we can ask whether a training choice is right, we have to know what, exactly, it&s;s doing. Learning theory is the part of the work that refuses to let us wave vaguely at “drive” or “reactivity” and instead requires that we describe contingencies, histories, and functions with care. Competence is ethics and ethi...

Application and effectiveness analysis of grouting reinforcement technology in building tilt correction

This study presents an AI‑enhanced integrated framework combining theoretical analysis, laboratory experiments, and field validation for correcting building tilt through grouting reinforcement. The methodology encompasses physics‑informed machine learning for slurry diffusion, artificial neural network‑based rheology,...

Preregistration: Computational principles of dopamine dynamics for reinforcement learning and action selection

A preregistration document for the project titled "Computational principles of dopamine dynamics for reinforcement learning and action selection"