Haitham Bou Ammar
Haitham Bou Ammar
Reinforcement Learning Team Leader @ Huawei London & H. Lecturer @ UCL
Email verificata su huawei.com - Home page
Titolo
Citata da
Citata da
Anno
Online multi-task learning for policy gradient methods
HB Ammar, E Eaton, P Ruvolo, M Taylor
International conference on machine learning, 1206-1214, 2014
1222014
Controller design for quadrotor uavs using reinforcement learning
H Bou-Ammar, H Voos, W Ertel
2010 IEEE International Conference on Control Applications, 2130-2135, 2010
842010
Reinforcement learning transfer via sparse coding
HB Ammar, K Tuyls, ME Taylor, K Driessens, G Weiss
Proceedings of the 11th international conference on autonomous agents and …, 2012
622012
Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment
HB Ammar, E Eaton, P Ruvolo, M Taylor
Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015
572015
An automated measure of mdp similarity for transfer in reinforcement learning
HB Ammar, E Eaton, ME Taylor, DC Mocanu, K Driessens, G Weiss, ...
Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014
552014
Automatically mapped transfer between reinforcement learning tasks via three-way restricted boltzmann machines
HB Ammar, DC Mocanu, ME Taylor, K Driessens, K Tuyls, G Weiss
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2013
52*2013
Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning
HB Ammar, E Eaton, JM Luna, P Ruvolo
Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015
512015
Safe policy search for lifelong reinforcement learning with sublinear regret
HB Ammar, R Tutunov, E Eaton
International Conference on Machine Learning, 2361-2369, 2015
512015
Nonlinear tracking and landing controller for quadrotor aerial robots
H Voos, H Bou-Ammar
Control Applications (CCA), 2010 IEEE International Conference on, 2136-2141, 2010
482010
Factored four way conditional restricted boltzmann machines for activity recognition
DC Mocanu, HB Ammar, D Lowet, K Driessens, A Liotta, G Weiss, K Tuyls
Pattern Recognition Letters 66, 100-108, 2015
422015
Evolution of cooperation in arbitrary complex networks
B Ranjbar-Sahraei, H Bou Ammar, D Bloembergen, K Tuyls, G Weiss
Proceedings of the 2014 international conference on Autonomous agents and …, 2014
412014
Theoretically-grounded policy advice from multiple teachers in reinforcement learning settings with applications to negative transfer
Y Zhan, HB Ammar
arXiv preprint arXiv:1604.03986, 2016
392016
Balancing two-player stochastic games with soft q-learning
J Grau-Moya, F Leibfried, H Bou-Ammar
arXiv preprint arXiv:1802.03216, 2018
362018
Reduced reference image quality assessment via boltzmann machines
DC Mocanu, G Exarchakos, HB Ammar, A Liotta
2015 IFIP/IEEE International Symposium on Integrated Network Management (IM …, 2015
302015
Distributed Newton method for large-scale consensus optimization
R Tutunov, H Bou-Ammar, A Jadbabaie
IEEE Transactions on Automatic Control 64 (10), 3983-3994, 2019
272019
Influencing Social Networks: An Optimal Control Study.
D Bloembergen, BR Sahraei, H Bou-Ammar, K Tuyls, G Weiss
ECAI 14, 105-110, 2014
262014
Optimizing complex automated negotiation using sparse pseudo-input gaussian processes
S Chen, HB Ammar, K Tuyls, G Weiss
Proceedings of the 2013 international conference on Autonomous agents and …, 2013
252013
An information-theoretic optimality principle for deep reinforcement learning
F Leibfried, J Grau-Moya, H Bou-Ammar
arXiv preprint arXiv:1708.01867, 2017
202017
Theory of cooperation in complex social networks
B Ranjbar-Sahraei, HB Ammar, D Bloembergen, K Tuyls, G Weiss
Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014
182014
Reinforcement learning transfer via common subspaces
HB Ammar, ME Taylor
International Workshop on Adaptive and Learning Agents, 21-36, 2011
18*2011
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20