reinforcement learning

Antimony-contact MoS2 FET gas sensors for reinforcement-learning–driven hazard perception at room temperature

Two-dimensional van der Waals semiconductors promise low-power chemical perception at room temperature, yet contact-limited on-currents and slow recovery impede closed-loop decision making in hazardous environments. Here we propose antimony (Sb)-contact two-dimensional (2D) monolayer MoS 2 field-effect transistors (FET...

Reproducibility Archive for Unified RL-Assisted PI Gain Adaptation in CC-CV Control of an SPS-DAB EV Fast Charger

This reproducibility archive contains the MATLAB/Simulink models, five frozen DDPG agents, training and evaluation scripts, harmonized PI versus RL-assisted PI comparisons, deterministic and randomized robustness studies, computational-burden and multirate analyses, numerical-convergence studies, cycle-averaged local-s...

Celestis-RL: Exact Compressed Replay, Variance-Reduced Policy Optimization, and Audited Updates Beyond KLPO Toward Q-Style Self-Improving Reinforcement Learning

Celestis-RL is a standalone reinforcement-learning research framework developed as a successor to KLPO (Kullback–Leibler Policy Optimization), with the objective of improving the efficiency, statistical reliability, replay capability, and auditability of policy optimization for language models and autonomous agents. It...

Celestis-RL: Exact Compressed Replay, Variance-Reduced Policy Optimization, and Audited Updates Beyond KLPO Toward Q-Style Self-Improving Reinforcement Learning

Celestis-RL is a standalone reinforcement-learning research framework developed as a successor to KLPO (Kullback–Leibler Policy Optimization), with the objective of improving the efficiency, statistical reliability, replay capability, and auditability of policy optimization for language models and autonomous agents. It...

OmarEssameldinMousa/LakePilot-Research-prototype: v1.1-revision2

LakeGym V5: A multi-agent reinforcement learning simulation environment for autonomous data lakehouse maintenance, optimizing Apache Iceberg compaction and partitioning.

The Imperative of Inclusive Literacy: Teachers Lived Experiences Fostering Struggling Readers Through the Lens of No Child Left Behind

This study explored the lived experiences of elementary teachers in supporting struggling readers within the context of inclusive literacy and examined the challenges they encountered and the instructional practices they employed to foster reading development. Using a qualitative phenomenological research design, the s...

Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning

Emergent Behavioral Consistency in a PersistentAutonomous Agent without Behavioral Prompts or Constraint-Based Safety Mechanisms.

UPDATE : 5. Codebase Verification: Zero Behavioral Instructions5.1 Keyword SearchA central claim of this work is that the surrounding architecture contains no behavioral instructions. This claim isverifiable. The following search was conducted across all five Python source files:Search patterns: 'you must', 'you should...

Amanollahi Geodesic Curvature Flow Solver

We introduce the official open-access repository of the Amanollahi Geodesic Curvature Flow Solver, a breakthrough continuous optimization paradigm for Boolean Satisfiability (SAT) that definitively bridges a 40-year theoretical gap in pure continuous constraint satisfaction. Historically, continuous optimization framew...

RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation

Heuristic and Optimal Synthesis of CNOT and Clifford Circuits

Efficiently implementing Clifford circuits is crucial for quantum error correction and quantum algorithms. Linear reversible circuits, equivalent to circuits composed of CNOT\xspace gates, have important applications in classical computing. In this work we present methods for CNOT\xspace and general Clifford circuit sy...

Reinforcement Learning-based Task Aware Denoising for Ambient and Instrument Noise in Das Seismic Data

Distributed acoustic sensing (DAS) offers advantages such as low cost, high sampling density, and minor geological structures identification. However, while highly sensitive fiber-optic sensors effectively capture valuable data, they also introduce complex noise fields containing simultaneous interference from hetero...