Diogo S. Carvalho

Joined

February 2022

Names

Diogo S. Carvalho (Preferred)

Diogo Carvalho

Emails

****@gmail.com (Confirmed)

****@tecnico.ulisboa.pt (Confirmed)

Personal Links

Google Scholar

Career & Education History

PhD student

Instituto Superior Técnico (tecnico.ulisboa.pt)

2020 – 2025

MS student

Instituto Superior Técnico (tecnico.ulisboa.pt)

2017 – 2019

Undergrad student

Instituto Superior Técnico (tecnico.ulisboa.pt)

2014 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Francisco S. Melo

2020 – 2025

PhD Advisor

Pedro A. Santos

2020 – 2025

Expertise

Reinforcement Learning

2020 – 2025

Publications

Multi-Bellman operator for convergence of $Q$-learning with linear function approximation
Diogo S. Carvalho, Pedro A. Santos, Francisco S. Melo
- Accepted by TMLR
- Readers: Everyone
Theoretical remarks on feudal hierarchies and reinforcement learning
Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos
- 26th European Conference on Artificial Intelligence
- Readers: Everyone
A new convergent variant of $Q$-learning with linear function approximation
Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos
- 02 Jan 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning
Pedro Pinto Santos, Diogo S. Carvalho, Miguel Vasco, Pedro A. Santos, Ana Paiva, Alberto Sardinha, Francisco S. Melo
- 02 Jan 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
A new convergent variant of $Q$-learning with linear function approximation
Diogo S. Carvalho
- 02 Jan 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
$Q$-learning with regularization converges with non-linear non-stationary features
Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning
Pedro Pinto Santos, Diogo S. Carvalho, Miguel Vasco, Francisco S. Melo, Alberto Sardinha, Pedro A. Santos, Ana Paiva
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone

Diogo S. Carvalho

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Multi-Bellman operator for convergence of $Q$-learning with linear function approximation

Theoretical remarks on feudal hierarchies and reinforcement learning

A new convergent variant of $Q$-learning with linear function approximation

Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning

A new convergent variant of $Q$-learning with linear function approximation

$Q$-learning with regularization converges with non-linear non-stationary features

Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning

Co-Authors