reinforcement learning

A Selective Review on Causal Reinforcement Learning with Unmeasured Confounders

Reinforcement learning (RL) is a fundamental framework for addressing sequential decision problems under uncertainty about system dynamics and outcomes. While RL has made significant progress in recent decades, deploying these methods in real-world scenarios remains challenging. A major obstacle is that standard RL alg...

A Sequential Decision Framework for Geosteering: Trajectory Selection Using Reinforcement Learning and Multi-Objective Optimization

Abstract Geosteering trajectory decisions are made sequentially as new logging-while-drilling data arrives, and each decision affects both the immediate trajectory and the information available for every decision that follows. Current practice handles this through manual, human-in-the-loop reinterpretation of a static...

Empirical Processes and Statistical Reinforcement Learning

Reinforcement Learning for Optimized Well Placement in Underground Hydrogen Storage

Abstract Well placement design for underground hydrogen storage (UHS) faces the challenge of balancing hydrogen recovery, costs, and operational constraints. This study develops a rule-guided reinforcement learning (RL) framework to jointly optimize well count and well locations for a depleted gas reservoir in Alberta,...

Risk-Constrained Authority-Coordinated Multi-Agent Reinforcement Learning for Safe and Energy-Efficient Drilling Optimization

Abstract Drilling-parameter optimization requires coordinated improvement of drilling efficiency and energy utilization while maintaining engineering safety under strongly coupled and time-varying operating conditions. This study proposes a Risk-Constrained Authority-Coordinated Multi-Agent Reinforcement Learning (RCAC...

Co-Optimization of Carbon Storage and Enhanced Oil Recovery Under Stochastic Geological and Market Uncertainty via Deep Reinforcement Learning

Abstract Carbon dioxide-enhanced oil recovery (CO2-EOR) coupled with geological carbon storage (GCS) has the potential to simultaneously improve hydrocarbon recovery and permanently sequester anthropogenic CO2. Achieving these dual objectives requires operational decision-making under significant geological and economi...

Innovative Classroom Management for Arabic Listening Instruction Based on Digital Transformation: A POAC Perspective of George R. Terry

Digital transformation has influenced Arabic language education, particularly listening instruction (mahārah al-istimā’). However, digital media such as Spotify does not automatically ensure effective learning and requires appropriate classroom management. This study examines classroom management in digitally transform...

Multi-agent Reinforcement Learning for Cooperative Control of Multiple Unmanned Surface Vehicle in Neutralizing Threat Vessels

This study proposes a cooperative capture system in which two allied unmanned surface vehicles (USVs) jointly deploy a capture net to intercept noncooperative vessels in naval environments. To overcome the limitations of traditional rule-based methods subjected to environmental uncertainties, a multi-agent reinforcemen...

Optimal Treatment Strategies for Prioritized Outcomes

Dynamic treatment regimes formalize precision medicine as a sequence of decision rules, one for each stage of clinical intervention, that map current patient information to a recommended intervention. Optimal regimes are typically defined as maximizing some functional of a scalar outcome's distribution, e.g., the distr...

EL-RAKHAWI CLOSED-LOOP AUTONOMOUS PLATFORM FOR PRECISION THERAPEUTICS AND VACCINE DISCOVERY VIA MICROPHYSIOLOGICAL SYSTEMS AND GENERATIVE AI

EL-RAKHAWI CLOSED-LOOP AUTONOMOUS PLATFORM V2.0: PRECISION THERAPEUTICS & VACCINE DISCOVERY Author: Dr. Mohamed Kamal Arafa El-RakhawiDOI: 10.5281/zenodo.23346881 A revolutionary closed-loop autonomous platform solving the 90% clinical failure rate in drug discovery by integrating generative AI, self-driving labs, and...

Statistical Inference in Reinforcement Learning: A Selective Survey

Reinforcement learning (RL) is concerned with how intelligence agents take actions in a given environment to maximize the cumulative reward they receive. In healthcare, applying RL algorithms could assist patients in improving their health status. In ride-sharing platforms, applying RL algorithms could increase drivers...

Autonomous Edge-Deployed AI System for Real-Time MPD Control and Optimization

Abstract Current Managed Pressure Drilling (MPD) systems rely heavily on operator interpretation, rule-based automation, and reactive responses to wellbore events, approaches fundamentally limited by human response times, static control algorithms, and inability to learn from operational experience. This paper introduc...