• Sakina Hazrat Sayyed
• Lokesh Banoth
• Bhanu Teja
• B.Vijayendar Reddy
• K.Sai Praneeth

This paper presents the outcomes of "Project Mario AI," which aimed to develop an AI agent capable of autonomously playing Super Mario Bros. using deep reinforcement learning (DRL) and convolutional neural networks (CNNs). Through the project, significant achievements were made in training an AI agent to navigate through early levels of the game, demonstrating proficiency in obstacle avoidance, pattern recognition, and strategic resource utilization. The study contributes insights into the application of advanced machine learning techniques in gaming and highlights both the potential and challenges of developing autonomous game-playing agents.

Deep Reinforcement Learning, Convolutional Neural Networks, Super Mario Bros, Game AI, Gameplay Automation.

"Leveraging Deep Reinforcement Learning in Super Mario Bros Gameplay", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d272-d276, April-2024, Available :http://www.jetir.org/papers/JETIR2404338.pdf

"Leveraging Deep Reinforcement Learning in Super Mario Bros Gameplay", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd272-d276, April-2024, Available at : http://www.jetir.org/papers/JETIR2404338.pdf