Alexandre Galashov
Alexandre Galashov
DeepMind
Verified email at google.com
Title
Cited by
Cited by
Year
Neural probabilistic motor primitives for humanoid control
J Merel, L Hasenclever, A Galashov, A Ahuja, V Pham, G Wayne, YW Teh, ...
arXiv preprint arXiv:1811.11711, 2018
462018
Meta reinforcement learning as task inference
J Humplik, A Galashov, L Hasenclever, PA Ortega, YW Teh, N Heess
arXiv preprint arXiv:1905.06424, 2019
382019
Information asymmetry in KL-regularized RL
A Galashov, SM Jayakumar, L Hasenclever, D Tirumala, J Schwarz, ...
arXiv preprint arXiv:1905.01240, 2019
302019
Information asymmetry in KL-regularized RL
A Galashov, SM Jayakumar, L Hasenclever, D Tirumala, J Schwarz, ...
arXiv preprint arXiv:1905.01240, 2019
302019
Task agnostic continual learning via meta learning
X He, J Sygnowski, A Galashov, AA Rusu, YW Teh, R Pascanu
arXiv preprint arXiv:1906.05201, 2019
262019
Exploiting hierarchy for learning and transfer in kl-regularized rl
D Tirumala, H Noh, A Galashov, L Hasenclever, A Ahuja, G Wayne, ...
arXiv preprint arXiv:1903.07438, 2019
202019
A 2-approximate algorithm to solve one problem of the family of disjoint vector subsets
AE Galashov, AV Kel’manov
Automation and Remote Control 75 (4), 595-606, 2014
132014
Meta-learning surrogate models for sequential decision making
A Galashov, J Schwarz, H Kim, M Garnelo, D Saxton, P Kohli, SM Eslami, ...
arXiv preprint arXiv:1903.11907, 2019
112019
Game Plan: What AI can do for Football, and What Football can do for AI
K Tuyls, S Omidshafiei, P Muller, Z Wang, J Connor, D Hennes, I Graham, ...
arXiv preprint arXiv:2011.09192, 2020
12020
Behavior Priors for Efficient Reinforcement Learning
D Tirumala, A Galashov, H Noh, L Hasenclever, R Pascanu, J Schwarz, ...
arXiv preprint arXiv:2010.14274, 2020
12020
Temporal Difference Uncertainties as a Signal for Exploration
S Flennerhag, JX Wang, P Sprechmann, F Visin, A Galashov, ...
arXiv preprint arXiv:2010.02255, 2020
12020
Transferring Task Goals via Hierarchical Reinforcement Learning
S Xie, A Galashov, S Liu, S Hou, R Pascanu, N Heess, YW Teh
12018
An Exact Pseudopolynomial Algorithm for a Problem of Finding a Family of Disjoint Subsets.
AE Galashov, A Kelmanov
DOOR (Supplement), 501-509, 2016
12016
Learning Dexterous Manipulation from Suboptimal Experts
R Jeong, JT Springenberg, J Kay, D Zheng, Y Zhou, A Galashov, N Heess, ...
arXiv preprint arXiv:2010.08587, 2020
2020
Importance Weighted Policy Learning and Adaption
A Galashov, J Sygnowski, G Desjardins, J Humplik, L Hasenclever, ...
arXiv preprint arXiv:2009.04875, 2020
2020
Information Theoretic Meta Learning with Gaussian Processes
MK Titsias, S Nikoloutsopoulos, A Galashov
arXiv preprint arXiv:2009.03228, 2020
2020
Learning motor primitives and training a machine learning system using a linear-feedback-stabilized policy
L Hasenclever, V Pham, J Merel, A Galashov
US Patent App. 16/586,087, 2020
2020
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL Download PDF
D Tirumala, H Noh, A Galashov, L Hasenclever, A Ahuja, G Wayne, ...
Meta reinforcement learning as task inference Download PDF
J Humplik, A Galashov, L Hasenclever, PA Ortega, YW Teh, N Heess
The system can't perform the operation now. Try again later.
Articles 1–19