Suivre
Shagun Sodhani
Shagun Sodhani
Facebook AI Research
Adresse e-mail validée de fb.com - Page d'accueil
Titre
Citée par
Citée par
Année
Toward trustworthy AI development: mechanisms for supporting verifiable claims
M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ...
arXiv preprint arXiv:2004.07213, 2020
3822020
Recurrent independent mechanisms
A Goyal, A Lamb, J Hoffmann, S Sodhani, S Levine, Y Bengio, ...
arXiv preprint arXiv:1909.10893, 2019
3502019
Vip: Towards universal visual reward and representation via value-implicit pre-training
YJ Ma, S Sodhani, D Jayaraman, O Bastani, V Kumar, A Zhang
arXiv preprint arXiv:2210.00030, 2022
1972022
Multi-task reinforcement learning with context-based representations
S Sodhani, A Zhang, J Pineau
International Conference on Machine Learning, 9767-9779, 2021
1782021
CLUTRR: A diagnostic benchmark for inductive reasoning from text
K Sinha, S Sodhani, J Dong, J Pineau, WL Hamilton
arXiv preprint arXiv:1908.06177, 2019
1702019
Invariant causal prediction for block mdps
A Zhang, C Lyle, S Sodhani, A Filos, M Kwiatkowska, J Pineau, Y Gal, ...
International Conference on Machine Learning, 11214-11224, 2020
1502020
Toward training recurrent neural networks for lifelong learning
S Sodhani, S Chandar, Y Bengio
Neural computation 32 (1), 1-35, 2020
120*2020
Reinforcement learning with competitive ensembles of information-constrained primitives
A Goyal, S Sodhani, J Binas, XB Peng, S Levine, Y Bengio
arXiv preprint arXiv:1906.10667, 2019
532019
Learning robust state abstractions for hidden-parameter block mdps
A Zhang, S Sodhani, K Khetarpal, J Pineau
arXiv preprint arXiv:2007.07206, 2020
52*2020
Conversational agent for search
B Krishnamurthy, S Sodhani, A Arora, M Aggarwal
US Patent 10,713,317, 2020
462020
Iirc: Incremental implicitly-refined classification
M Abdelsalam, M Faramarzi, S Sodhani, S Chandar
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
342021
Motif: Intrinsic motivation from artificial intelligence feedback
M Klissarov, P D'Oro, S Sodhani, R Raileanu, PL Bacon, P Vincent, ...
arXiv preprint arXiv:2310.00166, 2023
302023
Block contextual mdps for continual learning
S Sodhani, F Meier, J Pineau, A Zhang
Learning for Dynamics and Control Conference, 608-623, 2022
292022
TorchRL: A data-driven decision-making library for PyTorch
A Bou, M Bettini, S Dittert, V Kumar, S Sodhani, X Yang, G De Fabritiis, ...
arXiv preprint arXiv:2306.00577, 2023
272023
The neural race reduction: Dynamics of abstraction in gated networks
A Saxe, S Sodhani, SJ Lewallen
International Conference on Machine Learning, 19287-19309, 2022
242022
Evaluating logical generalization in graph neural networks
K Sinha, S Sodhani, J Pineau, WL Hamilton
arXiv preprint arXiv:2003.06560, 2020
232020
Identifying significant anomalous segments of a metrics dataset
SS Sheth, S Sodhani, R Bajaj, N Goel, M Awasthi, K Malik, H Rathi, ...
US Patent 10,129,274, 2018
222018
Toward trustworthy AI development: mechanisms for supporting verifiable claims (2020)
M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ...
arXiv preprint arXiv:2004.07213, 2020
202020
Recommendations based on feature usage in applications
N Puri, S Sodhani
US Patent 10,536,580, 2020
192020
An introduction to lifelong supervised learning
S Sodhani, M Faramarzi, SV Mehta, P Malviya, M Abdelsalam, ...
arXiv preprint arXiv:2207.04354, 2022
152022
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20