Prati
Samuel Gershman
Samuel Gershman
Potvrđena adresa e-pošte na fas.harvard.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
Building machines that learn and think like people
BM Lake, TD Ullman, JB Tenenbaum, SJ Gershman
Behavioral and brain sciences 40, e253, 2017
27722017
Model-based influences on humans' choices and striatal prediction errors
ND Daw, SJ Gershman, B Seymour, P Dayan, RJ Dolan
Neuron 69 (6), 1204-1215, 2011
17932011
The hippocampus as a predictive map
KL Stachenfeld, MM Botvinick, SJ Gershman
Nature Neuroscience 20, 1643-1653, 2017
7722017
Computational rationality: A converging paradigm for intelligence in brains, minds, and machines
SJ Gershman, EJ Horvitz, JB Tenenbaum
Science 349 (6245), 273-278, 2015
7212015
A tutorial on Bayesian nonparametric models
SJ Gershman, DM Blei
Journal of Mathematical Psychology 56, 1-12, 2012
6952012
Reinforcement learning and episodic memory in humans and animals: an integrative framework
SJ Gershman, ND Daw
Annual review of psychology 68, 101-128, 2017
4602017
Context, learning, and extinction
SJ Gershman, DM Blei, Y Niv
Psychological Review 117 (1), 197-209, 2010
4092010
The successor representation in human reinforcement learning
I Momennejad, EM Russek, JH Cheong, MM Botvinick, ND Daw, ...
Nature human behaviour 1 (9), 680-692, 2017
3822017
Reinforcement learning in multidimensional environments relies on attention mechanisms
Y Niv, R Daniel, A Geana, SJ Gershman, YC Leong, A Radulescu, ...
Journal of Neuroscience 35 (21), 8145-8157, 2015
3732015
The curse of planning: Dissecting multiple reinforcement learning systems by taxing the central executive
AR Otto, SJ Gershman, AB Markman, ND Daw
Psychological Science 24 (5), 751-761, 2013
3682013
Amortized Inference in Probabilistic Reasoning
SJ Gershman, ND Goodman
Proceedings of the 36th Annual Cognitive Science Society, 2013
3592013
Predictive representations can link model-based reinforcement learning to model-free mechanisms
EM Russek, I Momennejad, MM Botvinick, SJ Gershman, ND Daw
PLoS computational biology 13 (9), e1005768, 2017
3042017
Learning latent structure: carving nature at its joints
SJ Gershman, Y Niv
Current Opinion in Neurobiology 20 (2), 251-256, 2010
2992010
Toward a universal decoder of linguistic meaning from brain activation
F Pereira, B Lou, B Pritchett, S Ritter, SJ Gershman, N Kanwisher, ...
Nature communications 9 (1), 963, 2018
2872018
Retrospective revaluation in sequential decision making: A tale of two systems
SJ Gershman, AB Markman, AR Otto
Journal of Experimental Psychology: General 143, 182-194, 2014
2842014
Interplay of approximate planning strategies
QJM Huys, N Lally, P Faulkner, N Eshel, E Seifritz, SJ Gershman, ...
Proceedings of the National Academy of Sciences 112 (10), 3098-3103, 2015
2702015
Cost-benefit arbitration between multiple reinforcement-learning systems
W Kool, SJ Gershman, FA Cushman
Psychological science 28 (9), 1321-1333, 2017
2512017
Deep successor reinforcement learning
TD Kulkarni, A Saeedi, S Gautam, SJ Gershman
arXiv preprint arXiv:1606.02396, 2016
2322016
Deconstructing the human algorithms for exploration
SJ Gershman
Cognition 173, 34-42, 2018
2102018
The successor representation: its computational logic and neural substrates
SJ Gershman
Journal of Neuroscience 38 (33), 7193-7200, 2018
1912018
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20