Emilio Parisotto
Emilio Parisotto
Geverifieerd e-mailadres voor cs.cmu.edu - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Actor-mimic: Deep multitask and transfer reinforcement learning
E Parisotto, JL Ba, R Salakhutdinov
arXiv preprint arXiv:1511.06342, 2015
3852015
Generating images from captions with attention
E Mansimov, E Parisotto, JL Ba, R Salakhutdinov
arXiv preprint arXiv:1511.02793, 2015
2862015
Neuro-symbolic program synthesis
E Parisotto, A Mohamed, R Singh, L Li, D Zhou, P Kohli
arXiv preprint arXiv:1611.01855, 2016
2252016
Neural map: Structured memory for deep reinforcement learning
E Parisotto, R Salakhutdinov
arXiv preprint arXiv:1702.08360, 2017
1912017
The hanabi challenge: A new frontier for ai research
N Bard, JN Foerster, S Chandar, N Burch, M Lanctot, HF Song, E Parisotto, ...
Artificial Intelligence 280, 103216, 2020
1082020
Efficient Exploration via State Marginal Matching
L Lee, B Eysenbach, E Parisotto, E Xing, S Levine, R Salakhutdinov
arXiv preprint arXiv:1906.05274, 2019
712019
Stabilizing transformers for reinforcement learning
E Parisotto, F Song, J Rae, R Pascanu, C Gulcehre, S Jayakumar, ...
International Conference on Machine Learning, 7487-7498, 2020
662020
Active Neural Localization
DS Chaplot, E Parisotto, R Salakhutdinov
arXiv preprint arXiv:1801.08214, 2018
652018
Global pose estimation with an attention-based recurrent network
E Parisotto, D Singh Chaplot, J Zhang, R Salakhutdinov
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
522018
Gated path planning networks
L Lee, E Parisotto, DS Chaplot, E Xing, R Salakhutdinov
International Conference on Machine Learning, 2947-2955, 2018
48*2018
Concurrent Meta Reinforcement Learning
E Parisotto, S Ghosh, SB Yalamanchi, V Chinnaobireddy, Y Wu, ...
arXiv preprint arXiv:1903.02710, 2019
14*2019
Neural network for program synthesis
ASA Mohamed, R Singh, L Li, D Zhou, P Kohli, E Parisotto
US Patent 10,795,645, 2020
82020
Input-output example encoding
ASA Mohamed, P Kohli, R Singh, E Parisotto
US Patent 10,817,552, 2020
62020
Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation
E Parisotto, R Salakhutdinov
arXiv preprint arXiv:2104.01655, 2021
32021
On Proximal Policy Optimization's Heavy-tailed Gradients
S Garg, J Zhanson, E Parisotto, A Prasad, JZ Kolter, S Balakrishnan, ...
arXiv preprint arXiv:2102.10264, 2021
12021
Method and device for improved localization and mapping
E Parisotto, J Zhang, R Salakhutdinov, DS Chaplot
US Patent App. 16/990,510, 2020
2020
Method and device for improved localization and mapping
E Parisotto, J Zhang, R Salakhutdinov, DS Chaplot
US Patent 10,776,948, 2020
2020
Active Neural Localization
D Singh Chaplot, E Parisotto, R Salakhutdinov
arXiv e-prints, arXiv: 1801.08214, 2018
2018
PROPRIOCEPTIVE SPATIAL REPRESENTATIONS FOR GENERALIZED LOCOMOTION
J Zhanson, E Parisotto, R Salakhutdinov
STATE MARGINAL MATCHING WITH MIXTURES OF POLICIES
L Lee, B Eysenbach, E Parisotto, R Salakhutdinov, S Levine
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20