Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks

arXiv:2402.12067v1 Announce Type: new
Abstract: Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations …

abstract agent arxiv brain brain-inspired capabilities cs.lg cs.ne cs.ro environment inductive information location navigation performance prior tasks type visual visual navigation