Lessons from reinforcement learning for biological representations of space
Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. ‘head-centred’, ‘hand-centred’ and ‘world-based’). Recent advances in reinforcement learning demonstrate a quite different approach that may provide a more promising model for biological repre...
Main Authors: | Muryy, A, Narayanaswamy, N, Nardelli, N, Glennerster, A, Torr, PHS |
---|---|
Formato: | Conference item |
Idioma: | English |
Publicado em: |
Elsevier
2020
|
Registos relacionados
-
Deep Reinforcement Learning in complex environments
Por: Nardelli, N
Publicado em: (2021) -
Stabilising experience replay for deep multi-agent reinforcement learning
Por: Foerster, J, et al.
Publicado em: (2017) -
RanDumb: random representations outperform online continually learned representations
Por: Prabhu, A, et al.
Publicado em: (2025) -
Learning discriminative space-time actions from weakly labelled videos
Por: Sapienza, M, et al.
Publicado em: (2012) -
How robust is unsupervised representation learning to distribution shift?
Por: Shi, Y, et al.
Publicado em: (2023)