reinforcement learning

Replication Package for "The State of RL4SE: A Task-Oriented Review of Research on Reinforcement Learning for Software Engineering"

This record contains the replication package for the survey “The State of RL4SE: A Task-Oriented Review of Research on Reinforcement Learning for Software Engineering.” The package supports the study-identification, screening, classification, and artifact-availability results reported in the survey. It contains: • cand...

Is Physics Actually Derived From Path Availability? What if What Causes Physics is Merely the Recursion of Possibilities?

Physics, as we have inherited it, is a set of magnificent local dialects speaking past each other. Fermat tells us how light navigates. Hamilton tells us how matter navigates. Boltzmann tells us how heat navigates. Schrödinger tells us how amplitudes navigate. Einstein tells us how geometry navigates. None of these dia...

Project TALOS: Tactical Agentic Literature Orchestration System

Project TALOS is an autonomous research intelligence platform powered by deep reinforcement learning (DDDQN), multi-tier LLM orchestration, and the Grey Wolf Optimizer (GWO). It conducts end-to-end scientific literature discovery and evaluation across 16 academic APIs.

RLTG: Teacher-Guided, Hierarchical Multi-Reward Reinforcement Learning for Test Generation

The Limits of Language Are the Limits of Superintelligence: Why Large Language Models Can Traverse but Not Expand the Space of the Thinkable

Preprint · Version 1 · September 2026 · Not peer reviewed If the limits of language are the limits of the thinkable, then the possibility of linguistic superintelligence depends on whether a system can expand its own language. This paper argues that large language models (LLMs) cannot do so in a closed regime. We intro...

Protocol: WorkoutCPP - a pilot series of N-of-1 trials evaluating RL-generated adaptive exercise recommendations for pelvic pain management

Introduction: Chronic pelvic pain disorders (CPPDs) affect up to one in four reproductive-age women and are characterized by fluctuating, heterogeneous symptoms that complicate engagement in regular physical exercise. Standard programs rarely adjust to daily symptom variability. WorkoutCPP is a pilot series of N-of-1 t...

P300-CE as a Neural Indicator of Decision-Making Style and General Susceptibility to Behavioral Addiction

A preregistered, large-sample individual-differences study (N = 200 healthy adults) testing whether P300-CE — a newly discovered, large and sustained event-related brain response to critical gaming events — is a stable neural marker of behavioural-addiction vulnerability and exploration–exploitation decision style, and...

cvar-sf-repro: reproduction package for "A CVaR Safety Floor for Offline Reinforcement Learning under Unobserved Confounding: Duality and a Finite-Sample Validity Regime"

Reproduction package for the WAIMLAp 2026 paper A CVaR Safety Floor for Offline Reinforcement Learning under Unobserved Confounding: Duality and a Finite-Sample Validity Regime. It ships the confounded medical benchmark and its offline-data generator, the agents (CVaR-TRPO with the Safety-Floor acceptance gate, a CQL-s...

Corporate AI Training Program Template

A template for corporate AI training with role groups, learning objectives, governance practice, session design and post-training reinforcement.

Hierarchical attention-based graph deep reinforcement learning for scheduling single-armed cluster tools with multiple types of wafers

The State Extraction Graph (SEG) is proposed, which provides a significantly more concise structural representation than Petri nets for modeling multi-wafer fabrication processes and a Graph Deep Reinforcement Learning (G-DRL) method for scheduling cluster tools.

Project TALOS: Tactical Agentic Literature Orchestration System

Project TALOS is an autonomous research intelligence platform powered by deep reinforcement learning (DDDQN), multi-tier LLM orchestration, and the Grey Wolf Optimizer (GWO). It conducts end-to-end scientific literature discovery and evaluation across 16 academic APIs.

saberrrostami/cmfg-rl-reconfiguration-reproducibility: Reproducibility package v1.0.1

Reproducibility package accompanying the manuscript "Dynamic service composition reconfiguration in cloud manufacturing under limited shared recovery capacity: A reinforcement learning approach".