reinforcement learning

THE AUTONOMOUS TRANSDUCTION MACHINE: FROM SPIRAL GEOMETRY TO THE SOURCE CODE OF AN AI SYSTEM WITHOUT HUMAN SUPERVISION

Overview This preprint presents the Autonomous Transduction Machine (ATM), a computational system that translates the Primitive Architecture of Spiral Geometry into an executable autonomous kernel capable of acting, constructing, learning, and self-correcting without fine human supervision. The architecture reproduces,...

Autonomy and Decision-Making

In Chapter 2 , we explored the pivotal shift from rigid automation to the era of intelligent machines, introducing AI and Machine Learning, particularly Reinforcement Learning, as the core technologies enabling robots to learn. We learned that humanoids could begin to “see” and “learn to walk” through these advancement...

Multi-Objective Energy-Efficient Train Timetable Optimization in Urban Rail Transit via a Hybrid DRL-NSGA-III Framework

Urban rail transit systems face a pronounced contradiction between escalating traction energy consumption and passenger service quality under the carbon peaking and carbon neutrality goals. This study proposes a hybrid optimization framework offline combining deep reinforcement learning (DRL) and Non-dominated Sorting...

ThomasMBury/rl-reentry: v1.1.0-submission

This release corresponds to the code used for the manuscript: "Reinforcement learning discovers new mechanisms of reentry in excitable media" The repository contains code for cellular automaton simulations, reinforcement-learning environments and training scripts, policy evaluation, simulations in the geometries studie...

MineAgent: Deep Reinforcement Learning-based Testing for Minecraft

This package contains the extended test results for my Bachelor thesis MineAgent: Deep Reinforcement Learning-based Testing for Minecraft at the University of Trento, supervised by Fondazione Bruno Kessler (FBK) researchers.

Code for "Reinforcement learning discovers new mechanisms of reentry in excitable media"

Code associated with the manuscript “Reinforcement learning discovers new mechanisms of reentry in excitable media.” This archive corresponds to the current manuscript submission and includes the cellular automaton simulations, reinforcement-learning environments and training scripts, policy evaluation, simulations in...

eta-ctrl

A modular framework for rolling-horizon operational control using a Gym-compatible agent–environment abstraction. The framework enables integration of optimization-based agents (Pyomo), reinforcement learning agents (Stable-Baselines3), heuristic search methods, and rule-based controllers. Environments can be instantia...

PPORLD-EDNetLDCT: A Proximal Policy Optimization-based reinforcement learning framework for adaptive low-dose CT denoising

Low-dose computed tomography (LDCT) is critical for minimizing radiation exposure, but it often leads to increased noise and reduced image quality. Traditional denoising methods, such as iterative optimization or supervised learning, often fail to preserve image quality. To address these challenges, we introduce PPORLD...

Artificial Intelligence in Financial Forecasting: Accuracy and Limitations

This study critically investigates the evolving role of artificial intelligence (AI) in financial forecasting through a systematic literature review conducted across multiple reputable academic databases, and identifies persistent limitations, including model opacity, data quality concerns, and compliance challenges.

Surrogate-Assisted Deep Reinforcement Learning for Bi-Level Multi-Objective Capacity Sizing of Railway Collaborative Power Supply System

Artificial Intelligence and Machine Learning for Business Management

Artificial Intelligence and Machine Learning for Business Management is an academic textbook that presents an integrated understanding of artificial intelligence (AI), machine learning (ML), business analytics, managerial decision-making, strategy, digital transformation, responsible AI, governance, sustainability, and...

Effects of relational graph modularity and depth on the learning performance of neural networks

In recent years, graph-based machine learning techniques, such as reinforcement learning and graph neural networks, have garnered significant attention. While some recent studies have started to explore the relationship between the graph structure of neural networks and their predictive performance, they often limit th...