Raphael Köster
Raphael Köster
Google DeepMind
Verified email at
Cited by
Cited by
Inequity aversion improves cooperation in intertemporal social dilemmas
E Hughes, JZ Leibo, M Phillips, K Tuyls, E Dueñez-Guzman, ...
Advances in neural information processing systems 31, 2018
Big-loop recurrence within the hippocampal system supports integration of information across episodes
R Koster, MJ Chadwick, Y Chen, D Berron, A Banino, E Düzel, ...
Neuron 99 (6), 1342-1354. e6, 2018
Is Choice-Induced Preference Change Long Lasting?
T Sharot, SM Fleming, X Yu, R Koster, RJ Dolan
Psychological science 23 (10), 1123-1129, 2012
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
JZ Leibo, EA Dueñez-Guzman, A Vezhnevets, JP Agapiou, P Sunehag, ...
International Conference on Machine Learning, 6187-6199, 2021
The neural representation of prospective choice during spatial planning and decisions
R Kaplan, J King, R Koster, WD Penny, N Burgess, KJ Friston
PLoS biology 15 (1), e1002588, 2017
Human-centred mechanism design with Democratic AI
R Koster, J Balaguer, A Tacchetti, A Weinstein, T Zhu, O Hauser, ...
Nature Human Behaviour 6 (10), 1398-1407, 2022
Retrieval-based model accounts for striking profile of episodic memory and generalization
A Banino, R Koster, D Hassabis, D Kumaran
Scientific Reports 6 (1), 31330, 2016
Memo: A deep network for flexible combination of episodic memories
A Banino, AP Badia, R Köster, MJ Chadwick, V Zambaldi, D Hassabis, ...
arXiv preprint arXiv:2001.10913, 2020
Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents
R Köster, D Hadfield-Menell, R Everett, L Weidinger, GK Hadfield, ...
Proceedings of the National Academy of Sciences 119 (3), e2106028118, 2022
A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings
E Vinitsky, R Köster, JP Agapiou, EA Duéñez-Guzmán, AS Vezhnevets, ...
Collective Intelligence 2 (2), 26339137231162025, 2023
Role of Human-AI Interaction in Selective Prediction
E Bondi, R Koster, H Sheahan, M Chadwick, Y Bachrach, T Cemgil, ...
Proceedings of the AAAI Conference on Artificial Intelligence 36 (5), 5286-5294, 2022
Context-specific activation of hippocampus and SN/VTA by reward is related to enhanced long-term memory for embedded objects
E Loh, D Kumaran, R Koster, D Berron, R Dolan, E Duzel
Neurobiology of learning and memory 134, 65-77, 2016
Basal ganglia activity mirrors a benefit of action and reward on long-lasting event memory
R Koster, M Guitart-Masip, RJ Dolan, E Düzel
Cerebral Cortex 25 (12), 4908-4917, 2015
Action and valence modulate choice and choice-induced preference change
R Koster, E Duzel, RJ Dolan
PLoS One 10 (3), e0119682, 2015
Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences
R Köster, KR McKee, R Everett, L Weidinger, WS Isaac, E Hughes, ...
arXiv preprint arXiv:2010.09054, 2020
Stimulus novelty energizes actions in the absence of explicit reward
R Koster, TX Seow, RJ Dolan, E Düzel
PLoS One 11 (7), e0159120, 2016
The Good Shepherd: An Oracle Agent for Mechanism Design
J Balaguer, R Koster, C Summerfield, A Tacchetti
arXiv preprint arXiv:2202.10135, 2022
Melting Pot 2.0
JP Agapiou, AS Vezhnevets, EA Duéñez-Guzmán, J Matyas, Y Mao, ...
arXiv preprint arXiv:2211.13746, 2022
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
V Pătrăucean, L Smaira, A Gupta, AR Continente, L Markeeva, D Banarse, ...
arXiv preprint arXiv:2305.13786, 2023
Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors
R Köster, D Hadfield-Menell, GK Hadfield, JZ Leibo
arXiv preprint arXiv:2001.09318, 2020
The system can't perform the operation now. Try again later.
Articles 1–20