reinforcement learning

Implementasi Deep Reinforcement Learning untuk Optimasi Energi Sistem Panel Surya pada Penghitung Ikan Otomatis

Standalone battery-based photovoltaic systems can experience suboptimal energy utilization when energy-flow decisions rely on fixed control rules that do not adapt to changing operating conditions. This study implemented Deep Reinforcement Learning (DRL) based on a Deep Q-Network (DQN) on an ESP32 as a system-level ene...

Reward function compression facilitates goal-dependent reinforcement learning

Abstract Humans can uniquely assign value to novel, abstract outcomes to support reinforcement learning. However, this flexibility is cognitively costly and reduces learning efficiency. We propose that goal-dependent learning initially relies on capacity-limited working memory. With consistent experience, learners crea...

Human, AI, and Hybrid Ensembles for Detection of Adaptive, RL-based Social Bots

The use of reinforcement learning to dynamically adapt and evade detection is now well-documented in several cybersecurity settings including Covert Social Influence Operations (CSIOs), in which bots try to spread disinformation. While AI bot detectors have improved greatly, they are largely limited to detecting static...

Rosetta-OMNI: The Operative Control Law for Irreversible Systems (GKO x CPCA-B x IKS: Legitimacy Prior to Optimization, Time-to-Catastrophe, and Physical Enforcement) (Document 179)

Document 179 // SPEC-383 // Morandi Monograph Series Author: Marius Egerhei Torjusen (ORCID: 0009-0006-0431-6637)Affiliation: ReismannPoint Systems // Brahman Ventures, Risør, NorwayLocus: MorandiEngine Core Architecture Group (Locus Zero, Risør, Norge) Abstract Classical control theory and reinforcement learning presu...

Design and management of adaptive treatment strategies in healthcare using reinforcement learning

A Reward-Driven Decision Optimization Method for Biological Simulation

Self-Programming Artificial Intelligence: Autonomous Learning and Evolutionary Algorithms

This paper presents a hybrid framework for self-programming artificial intelligence (AI), integrating reinforcement learning (RL), genetic programming (GP), neural architecture search (NAS), and meta-learning to enable autonomous code evolution with minimal human intervention. The proposed system is designed to optimiz...

Editorial: Advancing sustainability and resilience in agri-food supply chains through multi-criteria decision-making methods

Agri-food supply chains (AFSCs) are found at the heart of many of the major challenges faced today, such as climate variability, geopolitical instability, digital disruption, and increased customer expectations for healthy, sustainably produced, yet affordable foods. In particular, smalland medium-sized enterprises (SM...

Safe reinforcement learning for aggregated demand response control of emerging flexible resources in active distribution networks

DeepRL-OLSR: A Deep Reinforcement Learning based Routing Mechanism for Energy-Efficient Data Transmission in WSN

Bridging Offline and Online Multi-Objective Reinforcement Learning

Bio-inspired exploration of butterfly wing morphology guides deep reinforcement learning optimization of robotic flight

How wing morphology shapes flight performance is a central question in functional biology and bio-inspired robotics, yet these relationships are difficult to isolate in living organisms. Here, we use a robotic butterfly with tunable wing geometry to systematically characterize morphology–performance relationships by co...