Comparing and Combining Curriculum Learning and Behaviour Cloning to train First person Shooter Agents

• Autor(a) principal: Almeida de Neves Marta, Pedro
• Data de Publicação: 2024
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/11110/2800
• topic: Reinforcement Learning; Unity; First-Person Shooter Games; Curriculum Learning; Behaviour Cloning

Artificial Intelligence bots are extensively used in multiplayer First-Person Shooter games. By using Machine Learning techniques, we can improve their performance and bring them to human skill levels. In this work, we focused on comparing and combining two Reinforcement Learning training architectures, Curriculum Learning and Behaviour Cloning, applied to a First-Person Shooter developed in the Unity Engine. We have created four team of three agents each: one team for Curriculum Learning, one for Behaviour Cloning, and another two for two different methods of combining Curriculum Learning and Behaviour Cloning. After completing the training, each agent was matched to battle against each agent of the other teams until each pairing had five wins or ten timeouts. In the end, results showed us that the agents trained with Curriculum Learning achieve better performance than the ones trained with Behaviour Cloning by a matter of 23.67% more average victories in one case. In terms of the combination attempts, not only did the agents trained with both devised methods have problems during training, but they also achieved insufficient results in battle, with an average of 0 wins.