reinforcement learning

The Cognitive Neuroscience of Category Learning

Category learning is an adaptive skill that enables organisms to efficiently interpret and respond to their environment. Evidence supports the existence of a declarative learning system that applies explicit rules and test hypotheses, and a procedural learning system that gradually forms stimulus-response associations...

KODEX — KDRIVE: RL-control

KODEX — KDRIVE (RL-control). reinforcement-learning controller — a feedback policy learned by the cross-entropy method in the twin plant loop; clamped by KGATE Benchmark: RL policy (cross-entropy): tracking **0.0551** vs naive 0.1225, twin-in-the-loop Part of KODEX, the Kronos Family of Codes — a benchmarked AI/ML fusi...

KODEX — KDRIVE: RL-control

KODEX — KDRIVE (RL-control). reinforcement-learning controller — a feedback policy learned by the cross-entropy method in the twin plant loop; clamped by KGATEBenchmark: RL policy (cross-entropy): tracking **0.0551** vs naive 0.1225, twin-in-the-loopPart of KODEX, the Kronos Family of Codes — a benchmarked AI/ML fusion...

Carbon-Aware Offline Reinforcement Learning for Joint Inventory Replenishment and Transportation Scheduling in Multi-Echelon Supply Chains

Joint replenishment and transportation decisions couple service, inventory, vehicle utilization, and carbon emissions over time. Offline reinforcement learning (RL) is attractive when operational logs exist but online exploration is unsafe; however, distribution shift and cumulative carbon constraints make direct offli...

RoboSuite Grasping

This repository contains the source code accompanying the paper “Noise Scheduling and Out-of-Distribution Generalisation in Deep Reinforcement Learning for 6-DOF Robotic Grasping.” The work evaluates three off-policy deep reinforcement learning configurations for a 6-DOF robotic grasping task using a Universal Robots U...

Autonomous Weighted Schema Direct Preference Optimization for Materials Discovery (Dataset and Code)

NOTE: Metadata and Authors will be updated upon de-anonymization by conference. Title: Autonomous Weighted Schema Direct Preference Optimization for Materials Discovery (dataset)Authors: REDACTED Files for post-training of Pharmacological discovery models using supervised fine-tuning (SFT) and reinforcement learning (R...

Accurate and explainable ICD-10-CM diagnosis coding through multi-stage model adaptation and evidence-guided verification

Results show that domain adaptation, task-aligned optimization, and evidence-guided verification can improve both coding accuracy and the auditability of model outputs.

The Unbreakable AI Fortress: A Multi-Layered Defense-in-Depth Framework for Superintelligence Alignment

Current paradigms in artificial superintelligence (ASI) alignment rely heavily on fluid statistical methods like Reinforcement Learning from Human Feedback (RLHF). However, these architectures remain systemically vulnerable to runtime "alignment faking," semantic exploitation, and adversarial jailbreaking. Drawing from...

VectorLLM++: A Unified Next-Token-Prediction MLLM for Dense Remote Sensing Perception and Vector Mapping

Intelligent Cloud Resource Allocation Using Reinforcement Learn-ing: Evaluating Accuracy, Adaptability, and Efficiency

Elastic clouds must continuously decide how much compute, memory and storage capacity to grant to workloads whose intensity and mix change from minute to minute, and classical threshold, queueing and forecasting controllers struggle to hold that balance without either over-provisioning or violating service level agreem...

Multi-Intersection Traffic Signal Controls in Smart Cities Based on Graph Convolution Collaborative Communication

A multi-intersection graph topology is constructed and the Graph Convolutional Network (GCN) and Long Short-Term Memory (LSTM) are used to extract features from the graph topology and predict changes in traffic flow and deep reinforcement learning is applied to autonomously control traffic signals.

An intelligent model for managing visual comfort and building energy consumption through facade control using reinforcement learning

Building facade characteristics have a significant influence on energy consumption for lighting and on occupant visual comfort, yet these two objectives frequently conflict with each other. Increasing the amount of incoming daylight reduces energy demand while simultaneously raising the risk of glare. Most prior studie...