Pablo Samuel Castro
TitleCited byYear
From taxi GPS traces to social and community dynamics: A survey
PS Castro, D Zhang, C Chen, S Li, G Pan
ACM Computing Surveys (CSUR) 46 (2), 1-34, 2013
Urban traffic modelling and prediction using large scale taxi GPS traces
PS Castro, D Zhang, S Li
International Conference on Pervasive Computing, 57-72, 2012
iBOAT: Isolation-based online anomalous trajectory detection
C Chen, D Zhang, PS Castro, N Li, L Sun, S Li, Z Wang
IEEE Transactions on Intelligent Transportation Systems 14 (2), 806-818, 2013
Real-time detection of anomalous taxi trajectories from GPS traces
C Chen, D Zhang, PS Castro, N Li, L Sun, S Li
International Conference on Mobile and Ubiquitous Systems: Computing …, 2011
Methods for computing state similarity in Markov decision processes
N Ferns, PS Castro, D Precup, P Panangaden
arXiv preprint arXiv:1206.6836, 2012
Dopamine: A research framework for deep reinforcement learning
PS Castro, S Moitra, C Gelada, S Kumar, MG Bellemare
arXiv preprint arXiv:1812.06110, 2018
Using Linear Programming for Bayesian Exploration in Markov Decision Processes.
PS Castro, D Precup
IJCAI 24372442, 2007
Smarter sampling in model-based Bayesian reinforcement learning
PS Castro, D Precup
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2010
Equivalence relations in fully and partially observable Markov decision processes
PS Castro, P Panangaden, D Precup
Twenty-First International Joint Conference on Artificial Intelligence, 2009
TF-Agents: A library for reinforcement learning in tensorflow
S Guadarrama, A Korattikara, O Ramirez, P Castro, E Holly, S Fishman, ...
Real time anomalous trajectory detection and analysis
L Sun, D Zhang, C Chen, PS Castro, S Li, Z Wang
Mobile Networks and Applications 18 (3), 341-356, 2013
Using bisimulation for policy transfer in MDPs
PS Castro, D Precup
Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010
Automatic construction of temporally extended actions for mdps using bisimulation metrics
PS Castro, D Precup
European Workshop on Reinforcement Learning, 140-152, 2011
A comparative analysis of expected and distributional reinforcement learning
C Lyle, MG Bellemare, PS Castro
Proceedings of the AAAI Conference on Artificial Intelligence 33, 4504-4511, 2019
A geometric perspective on optimal representations for reinforcement learning
M Bellemare, W Dabney, R Dadashi, AA Taiga, PS Castro, N Le Roux, ...
Advances in Neural Information Processing Systems, 4360-4371, 2019
An atari model zoo for analyzing, visualizing, and comparing deep reinforcement learning agents
FP Such, V Madhavan, R Liu, R Wang, PS Castro, Y Li, J Zhi, L Schubert, ...
arXiv preprint arXiv:1812.07069, 2018
Notions of state equivalence under partial observability
PS Castro, P Panangaden, D Precup
Proceedings of the 21st International Joint Conference on Artificial …, 2009
Bayesian exploration in Markov decision processes
PS Castro
McGill University, 2007
Distributional reinforcement learning with linear function approximation
MG Bellemare, NL Roux, PS Castro, S Moitra
arXiv preprint arXiv:1902.03149, 2019
On planning, prediction and knowledge transfer in Fully and Partially Observable Markov Decision Processes
PS Castro
McGill University (Canada), 2011
The system can't perform the operation now. Try again later.
Articles 1–20