reinforcement learning

Constitutional Intelligence as Formal Science The Karimov–Alekberli Framework as Mathematical Foundation for Governed Institutional Cognition

We present a synthesis of the Karimov–Alekberli (KA) Framework into a unified theory ofConstitutional Intelligence: the capacity of an adaptive system to make consequentialdecisions that are simultaneously governed, explainable, accountable, reconstructable,verifiable, and capable of learning without retroactive falsif...

Supplementary material from "Code-driven planning in grid worlds with large language models"

We propose an iterative programmatic planning (IPP) framework that solves grid-based tasks by using large language models (LLMs) to synthesize interpretable, executable programs that act as agent policies mapping environment states to action sequences, rather than relying on traditional search or reinforcement learning...

Power enhancement of a tuned inerter-equipped point-absorber wave energy converter using deep reinforcement learning

2026 Interim Teaching Statement Update

Zenodo Description This Interim 2026 Teaching Statement documents the next stage in the evolution of my teaching and learning philosophy, moving from INTEGRATE to SUSTAIN. It is a self-directed biennial update to a philosophy first developed in 2018 through the Harvard University Derek Bok Center for Teaching and Learn...

Adaptive Q-learning and cross-layer queue management for UAV-assisted vehicular routing

Reinforcement learning-guided multi-objective trajectory planning for obstacle avoidance in robotic manipulators

This paper proposes a reinforcement learning (RL)-guided multi-objective trajectory planning framework, termed RL-MOP-HNE, for a 6-DOF UR5 manipulator, which simultaneously minimizes path length, energy consumption, and execution time while satisfying collision-avoidance, kinematic, and dynamic constraints.

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...

A Performance-Based Hybrid RT–HT Model-Switching Mechanism in 5G Handover Optimization

The results show that the proposed Hybrid technique reduces handover failure by 82.2% under drift conditions, achieves 44% reduction in handover latency, and 66% reduction in ping-pong rate compared to MLSOHOT (RT).

Source Code for Adaptive Intelligent Resource Optimization in Wireless Sensor Networks Using Reinforcement Learning and Compressive Sensing

This repository contains the source code and computational implementation associated with the manuscript “Adaptive Intelligent Resource Optimization in Wireless Sensor Networks Using Reinforcement Learning and Compressive Sensing” submitted to Scientific Reports. The repository includes the proposed algorithm, preproce...

AI-Driven Dynamic Pricing and Advertising in E-Commerce Competition: A Differential Game Analysis of Coordination Reversal and Welfare

The framework provides an analytical characterization of a mechanism that can generate the lower-price coordination outcome reported in recent computational research, clarifying conditions under which multidimensional coordination can be associated with consumer-beneficial rather than purely anticompetitive outcomes.

Explainable AI (XAI) Framework for Transparent Human–Machine Job Scheduling in Hybrid Printing Operations

Hybrid printing operations integrate conventional manufacturing, additive manufacturing, and digital printing technologies, to create complex scheduling challenges arising from dynamic production environments, heterogeneous resources, and the limited transparency of conventional Artificial Intelligence (AI)-based sched...

Research on reinforcement learning stock trading strategy based on cost-aware information selection

Experimental results show that the CSI 300 Index is more stable in bear market and risk control; Ablation tests confirmed the key role of factor formation and adaptive selection in IS-MDP.