Ângelo Gregório Lovatto

According to our database, Ângelo Gregório Lovatto authored at least 4 papers between 2019 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Exploration Versus Exploitation in Model-Based Reinforcement Learning: An Empirical Study.

Ângelo Gregório Lovatto, Leliane Nunes de Barros, Denis Deratani Mauá

Proceedings of the Intelligent Systems - 11th Brazilian Conference, 2022

2021

Gradient Estimation in Model-Based Reinforcement Learning: A Study on Linear Quadratic Environments.

Ângelo Gregório Lovatto, Thiago Pereira Bueno, Leliane Nunes de Barros

Proceedings of the Intelligent Systems - 10th Brazilian Conference, 2021

2020

Decision-Aware Model Learning for Actor-Critic Methods: When Theory Does Not Meet Practice.

Ângelo Gregório Lovatto, Thiago Pereira Bueno, Denis Deratani Mauá, Leliane N. de Barros

Proceedings of the "I Can't Believe It's Not Better!" at NeurIPS Workshops, 2020

2019

Analyzing the Effect of Stochastic Transitions in Policy Gradients in Deep Reinforcement Learning.

Ângelo Gregório Lovatto, Thiago Pereira Bueno, Leliane Nunes de Barros

Proceedings of the 8th Brazilian Conference on Intelligent Systems, 2019