reinforcement learning

PEMBENTUKAN KEMANDIRIAN ANAK USIA 4-5 TAHUN DI TPA DAN TK IT AS-SALAM KOTA MALANG

This study was motivated by the importance of developing independence among children aged 4–5 years through habituation and environmental support. It aimed to describe the formation of child independence in the daycare and kindergarten environments of TK IT As-Salam Malang City and the factors influencing it. This rese...

Navigating the smart tourism era: a systematic review of how intelligent systems are shaping the future of travel

Tourism recommendation systems use artificial intelligence (AI), machine learning (ML), and data analytics to support travel decisions. This systematic literature review examines decision types, disciplinary distribution, themes, and research gaps in AI-based tourism recommendation research. Following the Preferred Rep...

EFFICIENT ENERGY MANAGEMENT IN NETWORKED MICROGRIDS USING MULTI-AGENT DEEP REINFORCEMENT LEARNING IN THE PRESENCE OF UNCERTAINTIES

Reinforcement Learning-Assisted Quantum Simulation of Many-Body Excited States and Real-Time Dynamics

Abstract The computation of electronic excited states and real-time quantum dynamics of many-Fermion systems is among the most promising applications of near-term quantum computing. In this work, we generalize the reinforcement learning contracted quantum eigensolver (RL-CQE), previously developed for ground-state prob...

Joint Optimization of Delay and Energy Efficiency for UAV Task Offloading and Cooperative Scheduling

The growing demand for multimedia services in Internet of Things (IoT) networks has significantly increased the traffic load on backhaul links, making Mobile Edge Caching (MEC) a key technology for reducing content delivery latency. Unmanned Aerial Vehicles (UAVs) can serve as mobile aerial caching nodes that complemen...

Implementing the Teaching Personal and Social Responsibility (TPSR) Model in Chinese Middle School: A Mixed-Methods Study

This study examined a six-month implementation of the Teaching Personal and Social Responsibility (TPSR) model in a Chinese middle school. Two Grade 8 classes were involved in the study, both of which were taught by the researcher. A mixed-methods design was employed to examine both the implementation process and the i...

Next-generation electrified powertrain technologies for sustainable mobility: A systematic review of architectures, intelligent control, energy storage, and grid integration

The global imperative to decarbonise road transport has required the automotive and energy sectors to reconceptualise vehicular powertrain engineering across all scales, from atomic-level electrochemistry to fleet-level grid interaction. This PRISMA-compliant systematic review synthesises 120 peer-reviewed publications...

A comprehensive survey on connectivity for IoT sensor networks

This paper presents various feature scopes used in wireless sensor networks (WSNs) and illustrates distinct approaches like relay node placement, efficient communication, machine-learning systems i.e. reinforcement learning, and heuristic techniques.

CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses

Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in untrusted tool outputs and can covertly alter the execution of a legitimate task. Defenses trained on fixed attacks may fail as an attacker changes its strategy, inject...

Temporal-Causal Inference for Reinforcement Learning via Automata Learning

Temporal-Causal Inference for Reinforcement Learning (TCIRL), a framework that jointly learns a control policy and infers the hidden temporal cause of the phase transition and recovers the correct cause DFA and matches the full-information baseline in both domains.

One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control

OSOL, which designates a focus domain at each iteration, uses the preceding checkpoint footprint to rank token-level rebound risk, and applies a drift-ranked, adaptively scaled correction within the standard GRPO update, is proposed, which suppresses the targeted cross-step output backtracking component.

Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning

A noisy-space action-value (Q-)function that assigns values to diffusion latents through the distribution of executed actions induced by the denoising process is introduced, which admits a precise semantic interpretation and derives a noisy-space policy gradient (NSPG) that optimizes noisy latents using only clean acti...