A Cross-Modality Transfer Reinforcement Learning Blind Agent on DareFightingICE

Thai Van Nguyen, Ibrahim Khan, Chollakorn Nimpattanavong, Ruck Thawonmas, Hai V. Pham

Abstract: This demo paper presents a deep reinforcement learning blind agent (blind agent) that uses only sound as the input on the DareFightingICE platform at the DareFightingICE Competition in IEEE CoG 2022 and 2023. A past study used reinforcement learning to train a blind agent and used it as the sample for the AI track of DareFightingICE Competition. However, this approach suffered from significant time expenses due to training the blind agent to recognize sounds and act in an end-to-end manner. To address this challenge, we propose a novel approach for blind agents where sound recognition and decision-making tasks are trained separately.