Lessons from reinforcement learning for biological representations of space

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...

Descripció completa

Dades bibliogràfiques
Autors principals:	Muryy, A, Narayanaswamy, N, Nardelli, N, Glennerster, A, Torr, PHS
Format:	Conference item
Idioma:	English
Publicat:	Elsevier 2020

Ítems similars

Deep Reinforcement Learning in complex environments
per: Nardelli, N
Publicat: (2021)

Stabilising experience replay for deep multi-agent reinforcement learning
per: Foerster, J, et al.
Publicat: (2017)

RanDumb: random representations outperform online continually learned representations
per: Prabhu, A, et al.
Publicat: (2025)

Learning discriminative space-time actions from weakly labelled videos
per: Sapienza, M, et al.
Publicat: (2012)

How robust is unsupervised representation learning to distribution shift?
per: Shi, Y, et al.
Publicat: (2023)

Learning discriminative space–time action parts from weakly labelled videos
per: Sapienza, M, et al.
Publicat: (2013)

Semantic-aware auto-encoders for self-supervised representation learning
per: Wang, G, et al.
Publicat: (2022)

Understanding representation learning for deep reinforcement learning
per: Le Lan, C
Publicat: (2023)

Exploring deictic representations in reinforcement learning
per: Finney, Sarah, 1974-
Publicat: (2014)

RanDumb: a simple approach that questions the efficacy of continual representation learning
per: Prabhu, A, et al.
Publicat: (2025)

Multi-agent common knowledge reinforcement learning
per: de Witt, C, et al.
Publicat: (2019)

A survey of reinforcement learning informed by natural language
per: Luketina, J, et al.
Publicat: (2019)

Value propagation networks
per: Nardelli, N, et al.
Publicat: (2019)

Time representation in reinforcement learning models of the basal ganglia
per: Gershman, Samuel J., et al.
Publicat: (2015)

Representation Discovery for Kernel-Based Reinforcement Learning
per: Zewdie, Dawit H., et al.
Publicat: (2015)

Representation discovery in non-parametric reinforcement learning
per: Zewdie, Dawit (Dawit Habtamu)
Publicat: (2014)

Lessons learned: eight years at the helm of Biology Open
per: Raff, J
Publicat: (2018)

Reinforcement learning in large state action spaces
per: Mahajan, A
Publicat: (2023)

Working memory as a representational template for reinforcement learning
per: Shibata, K, et al.
Publicat: (2024)

Lessons From The Molecular Biology Of Neonatal Hyperbilirubinaemia.
per: H., Van Rostenberghe, et al.

The vulnerability of heritage spaces : lessons from Mumbai
per: Phua, Joanna.
Publicat: (2009)

Innovation spaces: lessons from the United Nations
per: Bloom, L, et al.
Publicat: (2016)

Feasible measurement of learning in emergencies: lessons from Uganda
per: D’Sa, N, et al.
Publicat: (2019)

NeRF-VPT: learning novel view representations with Neural Radiance Fields via view prompt tuning
per: Chen, L, et al.
Publicat: (2024)

FedSR: a simple and effective domain generalization method for federated learning
per: Nguyen, AT, et al.
Publicat: (2023)

Lessons learned from research /
per: Sowder, Judith T., et al.
Publicat: (2002)

Reinforcement learning for bandits with continuous actions and large context spaces
per: Duckworth, P, et al.
Publicat: (2023)

Continual learning in low-rank orthogonal subspaces
per: Chaudhry, A, et al.
Publicat: (2020)

Multiple-instance learning with structured bag models
per: Warrell, J, et al.
Publicat: (2011)

Learning disentangled representations with semi-supervised deep generative models
per: Siddharth, N, et al.
Publicat: (2018)

Transferable Lessons from Biological and Supply Chain Networks to Autonomic Computing.
per: Calinescu, A
Publicat: (2007)

Learn what matters: cross-domain imitation learning with task-relevant embeddings
per: Franzmeyer, T, et al.
Publicat: (2023)

The body schema and the multisensory representation(s) of peripersonal space.
per: Holmes, N, et al.
Publicat: (2004)

Learning layered motion segmentations of video
per: Kumar, MP, et al.
Publicat: (2005)

Solving inefficiency of self-supervised representation learning
per: Wang, G, et al.
Publicat: (2022)

Phonetic-enriched text representation for Chinese sentiment analysis with reinforcement learning
per: Peng, Haiyun, et al.
Publicat: (2022)

Representations That Learn vs. Learning Representations
per: Liao, Qianli, et al.
Publicat: (2018)

Efficient online structured output learning for keypoint-based object tracking
per: Hare, S, et al.
Publicat: (2012)

Ambiguity modeling in latent spaces
per: Ek, CH, et al.
Publicat: (2008)

Efficient discriminative learning of parts-based models
per: Kumar, MP, et al.
Publicat: (2010)