reinforcement learning

ICoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model

Recursive AI, the prospect of artificial intelligence taking an increasingly complete role in building and improving artificial intelligence, has so far been demonstrated mostly on small models, bounded tasks, and fixed time budgets. A recent technical report by Yang and colleagues [1] asks a more demanding question: h...

Fault-Diagnosis-Aware Adaptive Policy Switching for Robust Map-Free Mobile Robot Navigation Under Sensor and Control Degradation

Heterogeneous sensor and control degradation can destabilize direct sensor-to-action navigation. This study presents a fault-diagnosis-aware adaptive policy-switching framework that combines a calibrated seven-class temporal health-state classifier with hysteretic routing among nominal, robust-fallback, and six fault-s...

Methodology Review: Intrusion Detection in Cybersecurity: A Study on Explainable Graphical Reinforcement Learning

This paper provides a structured methodological review of intrusion detection systems (IDS) in the field of cybersecurity, with particular attention to Explainable Graph-Structured Reinforcement Learning (XGRL). Instead of presenting experimental evaluations, the study concentrates on analyzing design principles and me...

Preference-guided graph reinforcement learning for multi-objective quality-aware hybrid flow shop scheduling with multilevel assembly

Product quality is crucial to the competitiveness of manufacturing enterprises. However, existing quality-aware scheduling studies mainly approximate product quality evolution using indirect factors such as processing time, making it difficult to characterize the integrated effects of equipment health conditions and op...

Windmill Problem Explained: 2011 IMO P2 and Garment Folding Robotics — E8 Intelligence Research

FINDING: The search results are mostly video titles and abstracts, not actual solutions. The only concrete mathematical content is the 2011 IMO windmill problem (P2) and a robotics paper on garment folding. No IMO 2025/2026 solutions are present. | MATH: Windmill problem (2011 IMO P2): Given a set of \(n\) points in ge...

Gait-parameterized RL for locomotion across morphologies and scales without reward retuning

Essays in machine learning and networks

Chapter 1: Machine Learning on Networks This chapter consists of three published papers, all developing and examining machine learning tools for graph-structured data.Graphs encode important structural properties of complex systems. Machine learning on graphs has therefore emerged as an important technique in research...

Research artifact for Automatic Generation of Unit Test Cases Based on Program Feedback Reinforcement Learning

This research artifact accompanies the manuscript Automatic Generation of Unit Test Cases Based on Program Feedback Reinforcement Learning by WeiDong Zhao. It contains reproducibility materials, not the unpublished manuscript full text. The artifact preserves an actually executed three-seed Qwen2.5-Coder-0.5B-Instruct...

Multi-agent Reinforcement Learning for Coordinated Emergency Building Sweeps

We develop a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework for coordinating emergency responders during building sweeps. The problem is formulated as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) that captures building topology, occupant vulnerability, dynamic hazards, and...

LQR Closed-Loop Reference Model-Based Residual Reinforcement Learning Control Methodology for Improving Longitudinal Speed Tracking Performance of Heavy-Duty Vehicles

Trajectory Planning and Optimization Methods for Intelligent Robots

Trajectory planning and trajectory optimization are the key technologies to realize the autonomous operation of intelligent robots. In order to solve the limitations of traditional manual teaching and offline planning in adapting to complex dynamic environments, insufficient movement smoothness and limited adaptability...

IMPLEMENTASI PEMBELAJARAN MENDALAM MELALUI PROJECT-BASED LEARNING YANG DIDUKUNG AI-BASED MICROLEARNING TERHADAP HASIL BELAJAR TEKNIK KOMPUTER DAN JARINGAN PADA MATERI SERANGAN SIBER KELAS XI SMK MUHAMMADIYAH 1 PEKANBARU

This study was motivated by the low learning outcomes of students in the cyberattack topic in the 11th-grade Computer and Network Engineering (TKJ) class at SMK Muhammadiyah 1 Pekanbaru. This study aimed to describe the implementation of Deep Learning through the Project-Based Learning (PjBL) model supported by AI-Base...