Comparing Human and AI Decision-Making Strategies in Strategic Games Using Reinforcement Learning

Ziad Karim Tabbouche

Comparing Human and AI Decision-Making Strategies in Strategic Games Using Reinforcement Learning

Author(s)	Ziad Karim Tabbouche
Country	India
Abstract	Strategic games have long served as experimental environments for studying intelligence, adaptation, and decision-making. Recent advances in reinforcement learning (RL) have enabled artificial intelligence systems to surpass human performance in complex games such as chess, Go, poker, and multiplayer strategy environments. Despite these achievements, significant differences remain between human and AI decision-making processes. Humans rely on intuition, bounded rationality, emotional judgment, and contextual reasoning, whereas reinforcement learning agents optimize actions through iterative reward maximization and policy learning. This paper presents a comparative analysis of human and AI decision-making strategies in strategic games using reinforcement learning frameworks. The study evaluates behavioral patterns, strategic adaptation, exploration mechanisms, and risk management across multiple competitive game environments. Experimental findings indicate that reinforcement learning agents achieve superior consistency and long-term optimization in structured settings, while human players demonstrate greater flexibility and adaptability under uncertain or novel conditions. The paper further examines how self-play learning, reward shaping, and opponent modeling influence AI strategy formation. Results suggest that hybrid systems integrating human-like reasoning with reinforcement learning optimization may provide more robust strategic decision-making models for future artificial intelligence applications.
Keywords	Reinforcement Learning, Strategic Games, Human Decision-Making, Artificial Intelligence, Multi-Agent Systems, Game Theory, Deep Reinforcement Learning, Human-AI Interaction, Strategic Reasoning, Adaptive Learning
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-08-10

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Comparing Human and AI Decision-Making Strategies in Strategic Games Using Reinforcement Learning

Share this