
Margarita Castro
email margarita.castro@uc.cl
Keywords from publications:
Reinforcement Learning Reward Machines Partial Observability Automata Learning Abstractions Non-markovian Environments Ver más...Network
Keywords from publications
Title | Year | Doi |
---|---|---|
Decision Diagrams for Discrete Optimization: A Survey of Recent Advances | 2022 | https://doi.org/10.1287/ijoc.2022.1170 |
A combinatorial cut-and-lift procedure with an application to 0-1 second-order conic programming | 2021 | https://doi.org/10.1007/s10107-021-01699-y |
Learning reward machines: A study in partially observable reinforcement learning | 2023 | https://doi.org/10.1016/j.artint.2023.103989 |
Optimization-based expansion planning for power and hydrogen systems with feedback from a unit commitment model | 2023 | https://doi.org/10.1016/j.apenergy.2023.121207 |
Optimal cleaning scheduling for large photovoltaic portfolios | 2024 | https://doi.org/10.1016/j.apenergy.2024.123760 |
Markov Chain-based Policies for Multi-stage Stochastic Integer Linear Programming with an Application to Disaster Relief Logistics | 2023 | https://doi.org/arXiv:2207.14779 |
School Co-Authors
-
álvaro Hugo Lorca2 publications
- 2 publications
- 1 publication
* Authors who are no longer vigent are not clickable.
External Co-Authors
-
Richard Valenzano1 publication
-
Ivan Astete1 publication
-
Ethan Waldie1 publication
-
Sheila A. Mcilraith1 publication
-
Toryn Q. Klassen1 publication
-
Lucas Maulen1 publication