reinforcement learning

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

Abstract 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...

Statistical Rigidity of Wigner-Dyson Eigenvalue Distributions in Gaussian Unitary Ensembles: The Spectral Integrity Operator and Selberg Automorphic Stabilization

Definition and exact evaluation of the Spectral Integrity Operator for Gaussian Unitary Ensemble (GUE) random matrices. Proves the identity T(E/I) = 1.000000 by combining the Wigner surmise normalization with the Dyson-Mehta spectral rigidity statistic at the James Arthur truncation scale. Establishes Selberg automorph...

QTrust-PPO: Confidence-Aware Finite-Shot Policy Optimization for Variational Quantum Reinforcement Learning

Initial public release of QTrust-PPO. This release contains the implementation notebooks, processed statistical results, figures, and table data for the QTrust-PPO experiments. Included components: Primary three-environment benchmark Confidence and rollback ablations Output-noise robustness experiments VQC depth analys...

Why Transformers Cannot Invent: The Manifold Confinement Problem and the Thermodynamic Engine of Scientific Discovery

The contemporary artificial intelligence research consensus posits that scaling test-time compute, Monte Carlo tree search, and Reinforcement Learning with Verifiable Rewards (RLVR / GRPO) will inevitably culminate in automated, superhuman scientific discovery. In this paper, we demonstrate the structural impossibility...

Poor Environments Make People More Prosocial to Humans but Not to AI: A Social Boundary of Foraging Theory

The richness of an environment can influence when individuals choose to act to help others. Recent research grounded in a foraging-theoretic framework has shown that, compared with rich environments, people are more willing to act to obtain rewards in poor foraging environments, and that this environmental influence is...

Exploring Hamiltonian Control of a Quantum Walk Environment via Reinforcement Learning: A Case Study on the Traveling Salesman Problem

The role of school culture in fostering responsibility in elementary school students

The purpose of this study is to analyze the effectiveness of school culture in shaping students’ attitudes toward responsibility at Seroja State Elementary School, Serang City. This research was conducted using a qualitative method, employing a case study approach. The research subjects were 35 sixth-grade students and...

Sparse Neural Code Representations for Reinforcement Learning with Linear Action-Value Function Approximation

Jev at the Agent Authorization Boundary: Evaluating TypeSafe's Decision Model and Its Reported RLCD Approach

TypeSafe describes Jev as a typed decision model trained using Reinforcement Learning for Calibrated Decisions (RLCD). We evaluate its behavior at an agent authorization boundary, where software must allow, hold, or deny a proposed action. A historical audit of 150 proposals motivates two separate paired comparisons: J...