Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{181050,
        author = {Anshuman Srivastava and Mr. Taneja Sanjay Dev Kishan},
        title = {Game AI Development using Reinforcement Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3296-3301},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181050},
        abstract = {Artificial Intelligence (AI) has become a 
pivotal element in modern video game development, 
significantly enhancing player engagement through 
dynamic gameplay and diverse strategies. Initially, 
game AI relied on rule-based logic and finite state 
machines, often resulting in repetitive and predictable 
behaviors. This predictability reduced the challenge 
and interest for players. Reinforcement Learning (RL), 
a branch of machine learning, presents a more adaptive 
solution by allowing AI agents to learn optimal 
decision-making strategies through trial-and-error 
interactions within the game environment. These agents 
receive feedback in the form of rewards and penalties, 
enabling continuous improvement. This paper 
investigates the core concepts of reinforcement learning 
and its implementation in the evolution of Game AI 
systems.},
        keywords = {reinforcement learning, game AI, deep Q networks, policy gradient, actor-critic, intelligent agents},
        month = {June},
        }