David Meger
David Meger
Associate Professor at McGill University
Potvrđena adresa e-pošte na - Početna stranica
Addressing function approximation error in actor-critic methods
S Fujimoto, H Hoof, D Meger
International conference on machine learning, 1587-1596, 2018
Deep reinforcement learning that matters
P Henderson, R Islam, P Bachman, J Pineau, D Precup, D Meger
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
Off-policy deep reinforcement learning without exploration
S Fujimoto, D Meger, D Precup
International conference on machine learning, 2052-2062, 2019
Curious george: An attentive semantic robot
D Meger, PE Forssén, K Lai, S Helmer, S McCann, T Southey, ...
Robotics and Autonomous Systems 56 (6), 503-511, 2008
Improved adversarial systems for 3d object generation and reconstruction
EJ Smith, D Meger
Conference on Robot Learning, 87-96, 2017
Geometrics: Exploiting geometric structure for graph-encoded objects
EJ Smith, S Fujimoto, A Romero, D Meger
arXiv preprint arXiv:1901.11461, 2019
Informed visual search: Combining attention and object recognition
PE Forssén, D Meger, K Lai, S Helmer, JJ Little, DG Lowe
2008 IEEE International Conference on Robotics and Automation, 935-942, 2008
Fine-grained categorization for 3d scene understanding
M Stark, J Krause, B Pepik, D Meger, JJ Little, B Schiele, D Koller
International Journal of Robotics Research 30 (13), 1543-1552, 2011
Simultaneous planning, localization, and mapping in a camera sensor network
I Rekleitis, D Meger, G Dudek
Robotics and Autonomous Systems 54 (11), 921-932, 2006
Automated spatial-semantic modeling with applications to place labeling and informed search
P Viswanathan, D Meger, T Southey, JJ Little, AK Mackworth
2009 Canadian Conference on Computer and Robot Vision, 284-291, 2009
An equivalence between loss functions and non-uniform sampling in experience replay
S Fujimoto, D Meger, D Precup
Advances in neural information processing systems 33, 14219-14230, 2020
Benchmark environments for multitask learning in continuous domains
P Henderson, WD Chang, F Shkurti, J Hansen, D Meger, G Dudek
arXiv preprint arXiv:1708.04352, 2017
Multi-view silhouette and depth decomposition for high resolution 3d object representation
E Smith, S Fujimoto, D Meger
Advances in Neural Information Processing Systems 31, 2018
Addressing function approximation error in actor-critic methods. arXiv 2018
S Fujimoto, H Van Hoof, D Meger
arXiv preprint arXiv:1802.09477, 1802
Vision-based goal-conditioned policies for underwater navigation in the presence of obstacles
T Manderson, JCG Higuera, S Wapnick, JF Tremblay, F Shkurti, D Meger, ...
arXiv preprint arXiv:2006.16235, 2020
Synthesizing neural network controllers with probabilistic model-based reinforcement learning
JCG Higuera, D Meger, G Dudek
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2018
3d shape reconstruction from vision and touch
E Smith, R Calandra, A Romero, G Gkioxari, D Meger, J Malik, M Drozdzal
Advances in Neural Information Processing Systems 33, 14193-14206, 2020
Semantic mapping for view-invariant relocalization
J Li, D Meger, G Dudek
2019 International Conference on Robotics and Automation (ICRA), 7108-7115, 2019
Learning legged swimming gaits from experience
D Meger, JCG Higuera, A Xu, P Giguere, G Dudek
2015 IEEE International Conference on Robotics and Automation (ICRA), 2332-2338, 2015
Explicit Occlusion Reasoning for 3D Object Detection.
D Meger, C Wojek, JJ Little, B Schiele
BMVC, 1-11, 2011
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20