Margarita Paz Castro
Margarita Paz Castro
Ph.D. Candidate, Industrial Engineering, University of Toronto
Verified email at - Homepage
Cited by
Cited by
Learning reward machines for partially observable reinforcement learning
R Toro Icarte, E Waldie, T Klassen, R Valenzano, M Castro, S McIlraith
Advances in Neural Information Processing Systems 32, 15523-15534, 2019
Linear and Integer Programming-Based Heuristics for Cost-Optimal Numeric Planning.
C Piacentini, MP Castro, AA Ciré, JC Beck
AAAI, 6254-6261, 2018
Training binarized neural networks using MIP and CP
RT Icarte, L Illanes, MP Castro, AA Cire, SA McIlraith, JC Beck
International Conference on Principles and Practice of Constraint …, 2019
An MDD-based lagrangian approach to the multicommodity pickup-and-delivery tsp
MP Castro, AA Cire, JC Beck
INFORMS Journal on Computing 32 (2), 263-278, 2020
Compiling Optimal Numeric Planning to Mixed Integer Linear Programming.
C Piacentini, MP Castro, AA Ciré, JC Beck
ICAPS, 383-387, 2018
Relaxed decision diagrams for cost-optimal classical planning
MP Castro, C Piacentini, AA Cire, JC Beck
Workshop HSDIP, ICAPS, 50-58, 2018
Searching for Markovian subproblems to address partially observable reinforcement learning
RT Icarte, E Waldie, TQ Klassen, R Valenzano, MP Castro, SA McIlraith
Proceedings of the 4th Multi-disciplinary Conference on Reinforcement …, 2019
Relaxed BDDs: An admissible heuristic for delete-free planning based on a discrete relaxation
MP Castro, C Piacentini, AA Cire, JC Beck
Proceedings of the International Conference on Automated Planning and …, 2019
Intruder alert! Optimization models for solving the mobile robot graph-clear problem
M Morin, MP Castro, KEC Booth, TT Tran, C Liu, JC Beck
Constraints 23 (3), 335-354, 2018
Empirical Confidence Models for Supervised Machine Learning
MP Castro, M Sellmann, Z Yang, N Virani
Canadian Conference on Artificial Intelligence, 105-117, 2020
Solving Delete Free Planning with Relaxed Decision Diagram Based Heuristics
MP Castro, C Piacentini, AA Cire, JC Beck
Journal of Artificial Intelligence Research 67, 607-651, 2020
A Combinatorial Cut-and-Lift Procedure with an Application to 0-1 Chance Constraints
MP Castro, AA Cire, JC Beck
arXiv preprint arXiv:2003.06363, 2020
Learning Reward Machines for Partially Observable Reinforcement Learning (Abridged Report)
RT Icarte, E Waldie, TQ Klassen, R Valenzano, AI Element, MP Castro, ...
The system can't perform the operation now. Try again later.
Articles 1–13