Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras

arXiv:2404.14064v1 Announce Type: new
Abstract: The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can leverage information from different camera perspectives to improve the performance of RL. However, hardware constraints may limit the availability of multiple cameras in real-world deployment. Additionally, cameras may become damaged in the real-world preventing access to all cameras that were used during …

abstract agents arxiv cameras cs.cv cs.lg hardware however image images information multiple performance person perspectives reinforcement reinforcement learning training type view