reinforcement learning

Research on asymmetric stochastic advertising differential games based on multi-agent deep reinforcement learning

Optimization of Underground Sublevel Stoping Layouts Considering Geological and Grade Uncertainty Using Deep Reinforcement Learning

From Power Concentration to Structured Light Generation: Scalable, Efficient and Generalizable Coherent Beam Combination With Model‐Based Reinforcement Learning

This work proposes a model‐based reinforcement learning (MBRL) framework that enables intelligent phase control by effectively emulating CBC system dynamics via a physics‐informed environment model, and establishes a powerful paradigm for integrating MBRL into high‐power optical field modulation.

Combating Web-Based E-Commerce Fraud Syndicates: Fairness-Aware Hypergraph Contrastive Fraud Detection with Multi-Dimensional Reinforcement Rewards

MRC, a novel semi-supervised model that integrates Multi-view Heterogeneous Hypergraph Contrastive learning (MHHC) and Multi-Dimensional Reinforcement reward driven Community detection (MDRC) for web-based e-commerce collusive fraud detection, is proposed.

Metanormative Theory for RL-Based Moral Agents

This paper aims to draw out ideas from recent work in metanormative theory that can be useful for designing artificial moral and value-aligned agents and examine the RL architecture through the lens of these ideas.

MoE-Pointer: Seq2Seq Reinforcement Learning for Dynamic Multi-Echelon Pickup-and-Delivery with Courier-Drone Relay

MoE-Pointer is proposed, a unified reinforcement learning framework that reformulates DM-PDP into a sequence-to-sequence generation task and introduces a Prior-Guided Soft Mask to guide exploration within the exponentially large action space.

Graph Attention Reinforcement Learning with Electrical Prior Knowledge for Distribution System Restoration

Case studies on the IEEE 34-bus system demonstrate that the proposed graph attention-based coupling-aware reinforcement learning method outperforms benchmark algorithms in training convergence, restored power, and online decision efficiency, enabling fast and effective distribution system restoration.

Left Turns at Unsignalized Intersections: Decision Making for Autonomous Vehicles Using Deep Reinforcement Learning with Game-Theoretic Reasoning

Results show that incorporating game-theoretic reasoning substantially improves decision stability, efficiency, and safety compared with a baseline DRL agent, achieving higher rewards, shorter maneuver times, and zero collisions across all scenarios.

Improving the Accuracy of Multi-Dimensional Cost Allocation in Public Hospitals Using a GNN-RL Hybrid Strategy Discrete Optimization Algorithm

A hybrid strategy discrete optimization algorithm based on Graph Neural Networks (GNN) and Reinforcement Learning (RL) that mines the complex correlation features between cost elements through GNN and uses RL to realize the learning of optimal allocation strategies in dynamic environments.

Research on Accurate Load Forecasting and Optimization Algorithm for Distribution Networks Based on Improved BiLSTM and DRL (High Load Density Areas)

An integrated algorithm based on improved Bidirectional Long Short-Term Memory and Deep Reinforcement Learning provides an effective solution for intelligent load prediction and adaptive energy management, offering practical support for electromagnetic energy distribution and resilient operation in next-generation smar...

Design of a Chinese Learning Platform Based on Knowledge Graph and Adaptive Question Answering

A Chinese learning platform integrating knowledge graph technology and adaptive question answering, developed to address fragmented knowledge structures, unclear learning paths, and insufficient personalized support in Chinese learning for non-native speakers is designed.

AoI-Guaranteed Dynamic Route Planning for Connected Vehicles

This paper presents a novel dual- factor approach that integrates travel time estimation and radio resource availability into an innovative route-planning scheme for connected vehicles (CVs) and shows that AGDRP outperforms the baseline scheme, which solely focuses on travel time optimization.