Joseph Modayil
Joseph Modayil
Openmind Research Institute & Keen AGI
Adresă de e-mail confirmată pe openmindresearch.org
Citat de
Citat de
Rainbow: Combining improvements in deep reinforcement learning
M Hessel, J Modayil, H Van Hasselt, T Schaul, G Ostrovski, W Dabney, ...
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
Vector-based navigation using grid-like representations in artificial agents
A Banino, C Barry, B Uria, C Blundell, T Lillicrap, P Mirowski, A Pritzel, ...
Nature 557 (7705), 429-433, 2018
Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction
RS Sutton, J Modayil, M Delp, T Degris, PM Pilarski, A White, D Precup
The 10th International Conference on Autonomous Agents and Multiagent …, 2011
Local metrical and global topological maps in the hybrid spatial semantic hierarchy
B Kuipers, J Modayil, P Beeson, M MacMahon, F Savelli
IEEE International Conference on Robotics and Automation, 2004. Proceedings …, 2004
Deep reinforcement learning and the deadly triad
H Van Hasselt, Y Doron, F Strub, M Hessel, N Sonnerat, J Modayil
arXiv preprint arXiv:1812.02648, 2018
Factoring the mapping problem: Mobile robot map-building in the hybrid spatial semantic hierarchy
P Beeson, J Modayil, B Kuipers
The International Journal of Robotics Research 29 (4), 428-459, 2010
Multi-timescale nexting in a reinforcement learning robot
J Modayil, A White, RS Sutton
Adaptive Behavior 22 (2), 146-160, 2014
Improving the recognition of interleaved activities
J Modayil, T Bai, H Kautz
Proceedings of the 10th international conference on Ubiquitous computing, 40-43, 2008
Bootstrap learning for object discovery
J Modayil, B Kuipers
2004 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2004
Bootstrap learning of foundational representations
BJ Kuipers, P Beeson, J Modayil, J Provost
Connection Science 18 (2), 145-158, 2006
The initial development of object knowledge by a learning robot
J Modayil, B Kuipers
Robotics and autonomous systems 56 (11), 879-890, 2008
Using the topological skeleton for scalable global metrical map-building
J Modayil, P Beeson, B Kuipers
2004 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2004
Autonomous development of a grounded object ontology by a learning robot
J Modayil, B Kuipers
Proceedings of the national conference on Artificial intelligence 22 (2), 1095, 2007
Ray interference: a source of plateaus in deep reinforcement learning
T Schaul, D Borsa, J Modayil, R Pascanu
arXiv preprint arXiv:1904.11455, 2019
Integrating Multiple Representations of Spatial Knowledge for Mapping, Navigation, and Communication.
P Beeson, M MacMahon, J Modayil, A Murarka, B Kuipers, B Stankiewicz
Interaction challenges for intelligent assistants, 1-9, 2007
Building local safety maps for a wheelchair robot using vision and lasers
A Murarka, J Modayil, B Kuipers
The 3rd Canadian Conference on Computer and Robot Vision (CRV'06), 25-25, 2006
On inductive biases in deep reinforcement learning
M Hessel, H van Hasselt, J Modayil, D Silver
arXiv preprint arXiv:1907.02908, 2019
Universal option models
C Szepesvari, RS Sutton, J Modayil, S Bhatnagar
Advances in Neural Information Processing Systems 27, 2014
Loss of plasticity in continual deep reinforcement learning
Z Abbas, R Zhao, J Modayil, A White, MC Machado
Conference on Lifelong Learning Agents, 620-636, 2023
Building machines that learn and think for themselves
M Botvinick, DGT Barrett, P Battaglia, N de Freitas, D Kumaran, JZ Leibo, ...
Behavioral and Brain Sciences 40, 2017
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20