Developing an Artificial Agent to play Games using Deep Reinforcement Learning

Bhardwaj, Chetan (2022) Developing an Artificial Agent to play Games using Deep Reinforcement Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

In Reinforcement Learning, Deep Q-Learning agents have seen great success with popular agents such as Alpha GO and Alpha Zero, these agents are constrained to discrete state space environments and are even prone to overestimation bias. To address these restrictions, we deployed Deep Deterministic Policy gradient and Soft Actor Critic off-policy algorithms in the Lunar Lander environment described in Zhao et al. (2020) research and compared their performance to Deep Q Networks. We observed that out of the three implemented algorithms, SAC outperformed both DQN and DDPG algorithms with a huge margin.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Computer Games. Video Games. Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	18 Jan 2023 18:01
Last Modified:	06 Mar 2023 16:27
URI:	https://norma.ncirl.ie/id/eprint/6090

Actions (login required)

View Item