سال انتشار:
2020
عنوان انگلیسی مقاله:
Lessons from reinforcement learning for biological representations of space
ترجمه فارسی عنوان مقاله:
درسهایی از یادگیری تقویت برای نمایش های بیولوژیکی فضا
منبع:
Sciencedirect - Elsevier - Vision Research, 174 (2020) 79-93. doi:10.1016/j.visres.2020.05.009
نویسنده:
Alex Muryya, N. Siddharthb, Nantas Nardellib, Andrew Glennerstera,⁎, Philip H.S. Torrb
چکیده انگلیسی:
Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. ‘headcentred’,
‘hand-centred’ and ‘world-based’). Recent advances in reinforcement learning demonstrate a quite
different approach that may provide a more promising model for biological representations underlying spatial
perception and navigation. In this paper, we focus on reinforcement learning methods that reward an agent for
arriving at a target image without any attempt to build up a 3D ‘map’. We test the ability of this type of
representation to support geometrically consistent spatial tasks such as interpolating between learned locations
using decoding of feature vectors. We introduce a hand-crafted representation that has, by design, a high degree
of geometric consistency and demonstrate that, in this case, information about the persistence of features as the
camera translates (e.g. distant features persist) can improve performance on the geometric tasks. These examples
avoid Cartesian (in this case, 2D) representations of space. Non-Cartesian, learned representations provide an
important stimulus in neuroscience to the search for alternatives to a ‘cognitive map’.
Keywords: Deep Reinforcement Learning | 3D spatial representation | Moving observer | Navigation | View-based | Parallax
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0