reinforcement learning

Reinforcement Learning for Reasoning Models

Reinforcement Learning‐Based Event‐Triggered Resilient Coordination Control for Spacecraft Formation Flying

ABSTRACT This paper studies resilient coordination control for a spacecraft formation subject to limited communication resources, admissible communication‐link faults, actuator faults, and uncertain nonlinear dynamics. A distributed data‐driven coordination scheme is developed using a resilient observer, event‐triggere...

A machine learning-based model for evaluating and optimizing efficiency in the green circular economy

A closed-loop energy efficiency assessment and global optimization architecture for green circular economy based on spatiotemporal graph attention mechanism and constrained multi-objective deep reinforcement learning and an adaptive feature correction operator is constructed to achieve lossless decoupling of transient...

Modeling ownership in non-human species: an argument for the domestic dog

The concept of ownership has been extensively examined within the context of human psychology, with a strong focus on how individuals represent relationships between people and objects (e.g., Boyer, 2023;Nancekivell et al., 2019). Comparative work has been relatively limited, with a small number of studies exploring th...

Structure-aware Reinforcement Learning Algorithms for Generative Models Post Training

Human Drama as Reality Operator: Revised Axiomatic Foundations of Narrative Realism

This work proposes a revised axiomatic foundation for narrative realism by treating human drama as a reality‑activating operator acting on fictional settings. The paper demonstrates that readers’ perception of realism in fiction is determined not by the ontological plausibility of the setting but by the existential urg...

A General Dynamic Theory of Competitive Signal Diversion

Competitive interaction among autonomous sub-agents in a complex adaptive system generates a structural dilemma: unconstrained rivalry accelerates innovation while simultaneously producing destructive entropy, whereas forced equilibrium removes destructive friction at the price of evolutionary stagnation. The present w...

Fundamentals of Reinforcement Learning

Optimization of Wushu Movement Learning and Training Methods Based on Deep Reinforcement Learning

The present research introduces WushuDRL-Net, an intelligent framework based on deep reinforcement learning (DRL) to enhance Wushu movement learning and training. The system employs the Proximal Policy Optimization with Motion Alignment Feedback (PPO-MAF) technique, which combines expert imitation, rhythm alignment, an...

ArchiveGene–UzMorphSim MultiDomain v1.1: An Uzbek Multi-Domain Resource for Semantic Similarity and Document Understanding

ArchiveGene–UzMorphSim MultiDomain v1.1 is a multi-domain Uzbek research dataset developed for semantic similarity, adaptive model routing, document understanding, layout-aware processing, and document-orientation analysis. The resource comprises a primary corpus of 2,000 text documents for semantic-similarity experime...

Multi-Agent Reinforcement Learning via Mean Field Game for Power Grid Fault Diagnosis & Prediction

Power grid fault diagnosis and prediction represent critical challenges in modern electrical infrastructure management, requiring rapid, accurate, and scalable decision-making under complex, dynamic conditions. This paper proposes a novel framework integrating MARL with MFG theory to address the inherent scalability li...

Behavior-Driven Tabular Reinforcement Learning Framework for Secure Next-Hop Routing in IoT Networks

simulation code of BRL model and operational algorithum of S1