reinforcement learning

A Case Study on the Robustness of Traffic Signal Control from a Data Science Perspective: The RobustLight Diffusion Reinforcement Learning Framework

Damaged sensor data, often caused by noise interference and data loss, impairs the decision-making accuracy of Deep Reinforcement Learning (DRL) traffic signal control models. This paper takes RobustLight (ICML 2025) as the core case and analyzes it from a data science perspective. We introduce DRL-based traffic signal...

AI Alignment Training Paradigms and Cross-Model Differences in AI Persuasive Behavior

Reinforcement learning from human feedback (RLHF) and constitutional artificial intelligence (CAI) are two ways to shape model behavior. Among them, CAI is built around avoiding different categories of harm, including racism, sexism, toxic, dangerous and illegal content. This article integrates the existing empirical r...

A new statistical feature-based adaptive deep reinforcement learning model for multi-objective task scheduling in IoT-fog environments

Dynamic control and optimization model of accounting information disclosure quality of listed companies based on deep reinforcement learning

The goal of this study is to develop an intelligent dynamic control and optimization model using Deep Reinforcement Learning (DRL) technology to address the issues of low efficiency and poor adaptability of static models in environmental Accounting Information Disclosure (AID) audits of listed companies. Based on the t...

Esports trainer

Real-Time Strategy (RTS) ist ein Genre von Videospielen, das nicht in Runden ablaeuft; dies impliziert, dass das Spiel standardmaessig in Echtzeit gespielt wird. RTS-Spiele erfordern kontinuierliche, sofortige Entscheidungsfindungen, was sich von Brettspielen wie Schach oder Go unterscheidet, bei denen Spieler Zeit hab...

Scored Before the Question Exists: What a Write-Time Importance Value in LLM Agent Memory Predicts, Why an Additive Term Is Not a Prior, and the Ablation the Canonical Architecture Did Not Run

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. An agent that stores what happens to it must decide what is worth storing and, later, what is worth reading back. The most-copied mechanism for the first decision is a scalar written at storage time: a language model is shown a record and asked how important it is....

Prior knowledge-assisted reinforcement learning for vehicle platoon control in cut-in scenarios

Energy Management for Ship Integrated Power Systems via Mode-Aware Safe Reinforcement Learning

Energy management in ship integrated power systems (IPSs) requires real-time dispatch of diesel generators, battery storage, and shore power under strict operational constraints. Existing deep reinforcement learning (DRL) approaches are economically competitive but cannot guarantee that device constraints are satisfied...

Applications of Artificial Intelligence in Industry 4.0/5.0

This Reprint presents recent advances in Artificial Intelligence (AI) and its applications within the evolving paradigms of Industry 4.0 and Industry 5.0. It brings together contributions addressing intelligent manufacturing, machine learning, computer vision, reinforcement learning, industrial automation, predictive a...

Emergent Behavioral Consistency in a PersistentAutonomous Agent without Behavioral Prompts or Constraint-Based Safety Mechanisms.

UPDATE : 5. Codebase Verification: Zero Behavioral Instructions5.1 Keyword SearchA central claim of this work is that the surrounding architecture contains no behavioral instructions. This claim isverifiable. The following search was conducted across all five Python source files:Search patterns: 'you must', 'you should...

Value-Aware Estimation of Diffusion Systems for Continuous-Time Reinforcement Learning: Surrogate Loss and Financial Applications

Abstract. We estimate diffusion systems modeled by SDEs to solve optimal control problems in a continuous-time model-based reinforcement learning framework. Instead of minimizing a statistical loss, we estimate models by reducing the mismatch between the model-based value process and empirical rewards under a given pol...

Cross-attention multi-scale graph reinforcement learning for dynamic flexible job-shop scheduling under hybrid uncertainty