PDI - Resultado de Búsqueda

Rodrigo Andrés Toro Icarte

Assistant Professor

Pontificia Universidad Católica de Chile

Santiago, Chile

Artificial Intelligence, Machine Learning, Reinforcement Learning, Deep Learning, Discrete Optimization, Knowledge Representation, and Commonsense Reasoning.

Computer Science, UNIVERSITY OF TORONTO. Canada, 2018
Artificial Intelligence, UNIVERSITY OF TORONTO. Canada, 2022
Computer Science, PONTIFICIA UNIVERSIDAD CATOLICA DE CHILE. Chile, 2015

Assistant professor Full Time

PONTIFICIA UNIVERSIDAD CATOLICA DE CHILE

Engineering

Chile

2021 - At present


Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning Article JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH (2022)
Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning Tapia, Tomas Felipe; NEYEM, ANDRES Article ISI APPLIED SCIENCES-BASEL (2022)
Training Binarized Neural Networks Using MIP and CP Icarte, Rodrigo Toro; McIlraith, Sheila A.; Schiex, T; DeGivry, S Article ISI SOCIAL COMPUTING AND SOCIAL MEDIA: APPLICATIONS IN EDUCATION AND COMMERCE, SCSM 2022, PT II (2019)


Be Considerate: Avoiding Negative Side Effects in Reinforcement Learning Alizadeh Alamdari, Parand ConferencePaper (2022)
Real-Time Heuristic Search with LTLf Goals Middleton, Jaime ConferencePaper (2022)
Interpretable Sequence Classification via Discrete Optimization Shvo, Maayan; Li, Andrew ConferencePaper (2021)
LTL2Action: Generalizing LTL Instructions for Multi-Task RL Vaezipoor, Pashootan ConferencePaper (2021)
Symbolic Plans as High-Level Instructions for Reinforcement Learning Yan, Xi ConferencePaper (2020)
Learning Reward Machines for Partially Observable Reinforcement Learning Waldie, Ethan; Castro, Margarita ConferencePaper (2019)
LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning Camacho, Alberto ConferencePaper (2019)
Advice-Based Exploration in Model-Based Reinforcement Learning ConferencePaper (2018)
Teaching Multiple Tasks to an RL Agent using LTL ConferencePaper (2018)
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning ConferencePaper (2018)
How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval ConferencePaper (2017)

Margarita Castro

Assistant Professor

Ingeniería Industrial y de Sistemas

Pontificia Universidad Católica de Chile

Santiago, Chile

Rodrigo Toro

Assistant Professor

Computer Science

Pontificia Universidad Católica de Chile

Santiago, Chile

Rodrigo Andrés Toro Icarte

Líneas de Investigación

Educación

Computer Science, UNIVERSITY OF TORONTO. Canada, 2018

Artificial Intelligence, UNIVERSITY OF TORONTO. Canada, 2022

Computer Science, PONTIFICIA UNIVERSIDAD CATOLICA DE CHILE. Chile, 2015

Experiencia Académica

Assistant professor Full Time

Article (3)

Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

Training Binarized Neural Networks Using MIP and CP

ConferencePaper (11)

Be Considerate: Avoiding Negative Side Effects in Reinforcement Learning

Real-Time Heuristic Search with LTLf Goals

Interpretable Sequence Classification via Discrete Optimization

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Symbolic Plans as High-Level Instructions for Reinforcement Learning

Learning Reward Machines for Partially Observable Reinforcement Learning

LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning

Advice-Based Exploration in Model-Based Reinforcement Learning

Teaching Multiple Tasks to an RL Agent using LTL

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval

Margarita Castro

Rodrigo Toro