reinforcement learning

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 It contains reproducibility materials, not the unpublished manuscript full text.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...

Adaptive multi-agent optimization in intelligent-connected vehicles based on deep reinforcement learning

In order to provide offloading services for computationally demanding and time-sensitive operations on vehicles, multi-access edge computing has emerged as a successful paradigm. However, there are typically spatiotemporal load mismatches across edge servers due to significant vehicle mobility. As a result, task migrat...

THE EL-RAKHAWI MODULAR AUTONOMOUS BIOMANUFACTURING SYSTEM (MABS) A Compact, Closed-Loop, AI-Guided Platform for Decentralized Production of Cellular Therapies, Vaccines, and Diagnostic Reagents

The El-Rakhawi Modular Autonomous Biomanufacturing System (MABS) (DOI: 10.5281/zenodo.23305330) presents a groundbreaking compact platform for decentralized therapeutic production, integrating four core subsystems within a footprint under 4 square meters: (1) Modular Microfluidic Cell Processing Unit (MMCPU) with dispo...

Comparing Stochastic Training Environments for Deep Reinforcement Learning with Deep Q-network: Learning Stability and Transfer to Real Data

The paper investigates how the choice of a generative stochastic model of the training environment affects the numerical stability of the learning and the transfer of the Double DQN policy to real time series. Four environments — GBM, GARCH(1,1)-t, Minimal Neural SDE, and Neural Jump-Diffusion — are compared, created o...

MiguelSantPasc/Code_AdvSSM: v1.0.0 – Adversarial Observations in State-Space Models for Robust RL Copiar

Code release – v1.0.0 This release contains the source code accompanying the manuscript "Adversarial Observations in State-Space Models for Robust Reinforcement Learning" by M. Santos-Pascual and D. Ríos Insua. The repository provides implementations and experimental scripts for studying adversarial perturbations of ob...