reinforcement learning

HALSI: Hierarchical adaptive latent skill inference for temporal abstraction in reinforcement learning

Dynamic federated multi-agent planning under partial observability and network instability for real-time edge applications

This paper introduces Dynamic Federated Multi-Agent Planning (DFMAP), a novel framework that integrates federated reinforcement learning (FRL) with partially observable Markov decision processes (POMDPs) for real-time decision-making in volatile edge environments.

Can Artificial Intelligence be Socratic?

It is argued that SI construct gives the philosophy of AI a normative vocabulary that interfaces classical philosophy with current machine-learning practice.

MIRAI-EDU-D: A Software-Free Discrete-Electronics Educational Robot for Tangible STEAM Formative Assessment

This article presents MIRAI-EDU-D, a software-free adaptive educational micro-robot designed to support tangible formative assessment in STEAM activities for primary and secondary education. The proposal addresses two current tensions: the expansion of educational robotics as a resource for active learning and computat...

Cache-Fused Kinematic Rails: Ex-Ante Silicon Alignment via In-Vivo KV-Cache Metric Grafting

Abstract of Cache-Fused Kinematic Rails: Ex-Ante Silicon Alignment via In-Vivo KV-Cache Metric Grafting Current Large Language Model (LLM) alignment relies primarily on post-hoc, output-level correction mechanisms such as external API meta-governors, Reinforcement Learning from Human Feedback (RLHF), or post-generation...

Energy-aware routing in underwater wireless sensor networks via temporal graph neural network and reinforcement learning

Underwater wireless sensor networks (UWSN) are characterized by dynamic network topology, limited node energy, and constrained communication capabilities, which make reliable and energy-efficient data transmission a significant challenge in time-varying underwater environments. Conventional routing approaches, usually...

DGend/justgrpo-smaller-essential: v1.1.0

Code accompanying the manuscript "Standard Group Relative Reinforcement Learning Is Unstable on Small Masked-Diffusion Language Models: A Controlled Study and Five Rejected Explanations," submitted to Scientific Reports. Includes the reinforcement learning driver, the supervised fine-tuning and evaluation scripts writt...

A model–free reinforcement learning framework for statistical process monitoring with variable sampling rate

Generalization from early to middle childhood

Generalization enables individuals to apply knowledge derived from past experiences in novel situations, yet it is unclear whether common experimental paradigms probe the same underlying ability in early to middle childhood. We assessed 84 children aged 4, 6, and 8 years on four paradigms, namely statistical learning,...

EdgeEngine AWARE: an application- and energy-aware simulation environment for reinforcement learning in energy-harvesting Edge IoT systems

A Gymnasium environment in which an agent schedules the sensing and the transmissions of an energy-harvesting embedded node from hardware-measurable quantities only. Three application domains (smart agriculture with a solar panel, indoor air quality with an indoor photovoltaic cell, industrial motor monitoring with a t...

Study record and reproduction code for a survey of evaluation design and disclosure requirements in reinforcement learning-based route guidance

Reproduction material for the survey "Study-Area Boundaries in Reinforcement Learning-Based Route Guidance: A Survey of Evaluation Design and Disclosure Requirements" by Donghoun Lee. The package holds the study record of the 93 reviewed studies, one row per study with the sentence of the research article behind each r...

Dynamic Potential Field Exploration Framework: An Internal Value Construction Method Based on State Visitation History

Effective exploration in sparse-reward environments is one of the important challenges in reinforcement learning. Existing methods typically rely on external reward signals or intrinsic motivation mechanisms derived from rewards to establish behavioral value. However, when environmental feedback is extremely limited, a...