reinforcement learning

A Reinforcement Learning Supervisor with Dynamic Performance-Metric Weighting for Cryptocurrency Portfolio Management

Uncertainty-aware model-enhanced soft actor-critic for conformal coating parameter optimization

Conformal coating optimization requires control of multiple application parameters to achieve target thickness and coverage uniformity, with spray atomization settings (atomization valve control) playing a crucial role in droplet formation and material deposition. Traditional manual tuning yields a low success rate...

Comprehensive Chemical Space Exploration in De Novo Drug Design: An Algorithmically Constrained, Parallel Dual-Paradigm Framework Validated on BACE1

Isolated de novo drug design paradigms carry inherent vulnerabilities: ligand-based (LBDD) models risk unreliable extrapolation beyond their training domain, while structure-based (SBDD) genetic algorithms accumulate molecular size-bias across evolutionary generations. Furthermore, on structurally complex targets, depl...

Possibilities of using software complexes with elements of artificial intelligence in fortification

Modern armed conflicts require high speed and validity of planning engineering equipment of defense lines. The article is devoted to the analysis of the implementation of software complexes with elements of artificial intelligence (AI) as decision support systems (DSS) in fortification planning. The concept of GeoAI is...

Hierarchical deep reinforcement learning for multi-timescale Robotic Mobile Fulfillment System optimization

Conditional Safety Certification for Multi-Objective Energy–Water Microgrid Dispatch via Joint-Trajectory Conformal Uncertainty, Backward Viability, and Runtime Shielding

This dataset provides the code, frozen experimental configurations, trained-controller checkpoints, sealed synthetic benchmark, reproducibility manifests, and numerical analysis artifacts supporting the manuscript entitled “Conditional Safety Certification for Multi-Objective Energy–Water Microgrid Dispatch via Joint-T...

E2E-DRTO: a micro end-to-end routing and transmission collaborative optimization method for large scale networks

With the rapid development of large-scale networks such as data center networks and wide area networks, how to achieve efficient traffic scheduling under complex topologies and dynamic traffic demands has become a key issue. Traditional methods typically separate routing selection from transmission rate control, or rel...

Learning Adaptive Search with Reinforcement Learning for Small and Fast Object Tracking

AdaSAM2 is introduced, a framework that formulates adaptive search-region selection as a sequential decision-making problem that employs an event-driven reinforcement learning policy that selects the cropping scale only during initialization and unreliable tracking states, while reusing the previous configuration durin...

Explainable Reinforcement Learning for Transmission-Corridor Reinforcement under Renewable Integration: An Austrian Case Study

Transmission expansion planning must balance investment cost, network loading, and renewable-energy integration under uncertain operating conditions. This study investigates whether explainable reinforcement learning can support the allocation of additional capacity to existing transmission corridors in a stylised Aust...

Artificial Intelligence, Machine Learning, and Deep Learning Concepts, Methods, and Real-World Impact

This chapter presents an accessible yet technically grounded overview of the relationship among AI, ML, and DL, tracing their historical development from early symbolic reasoning and theoretical foundations to modern neural networks and transformer-based systems.

rslcpp - ROS Simulation Library for C++

rslcpp - the ROS simulation library for C++ - lets you turn a set of existing ROS 2 nodes into a deterministic simulation. Instead of the asynchronous, multi-process default execution of ROS 2, rslcpp aggregates all participating nodes in a single process and drives them through a custom executor under an explicit simu...

Botanical Context Biasing for Experience-Dependent Neuroplasticity: A Two-Timescale Hypothesis of Directional Reinforcement During Psilocybin-Induced Plasticity

Psilocybin and related psychedelics can induce transient states of increased neural variability, context sensitivity, and plasticity-associated signaling. We hypothesize that selected companion botanicals can be composed with psilocybin to create a reproducible physiological and experiential lens, a botanical context,...