Scholar
Rafael Rodriguez-Sanchez
Google Scholar ID: ONxoqRUAAAAJ
Brown University
Citations & Impact
Citations
40
H-index
4
i10-index
1
Publications
9
Co-authors
5
list available
Publications
Resume
Academic Achievements
- Preprints: 'From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning'; Conferences: 'Intrinsically Motivated Discovery of Temporally Abstract Graph-based Models of the World', presented at the 2nd Reinforcement Learning Conference (RLC) 2025.
Research Experience
- Interned at Amazon Alexa during Summer 2021, working in the Dialogue Research group, using large language models (LLMs) for semantic parsing via supervised finetuning (SFT) and reinforcement learning (RL) in task-oriented dialog systems.
Education
- Ph.D. student in Computer Science at Brown University, advised by George Konidaris; Master's degree in Computer Science from Politecnico di Milano, where he worked with Marcello Restelli and Nicola Gatti at AIRLAB; Bachelor's degree in Electronic Engineering from Universidad Simon Bolivar, Caracas, Venezuela.
Background
- His research interests include representation learning and reinforcement learning (RL), with a focus on state representation learning directly from high-dimensional observations. His work also explores the intersection of natural language and RL, leading to the development of the RLang framework for communicating task-specific knowledge to RL agents through language.
Miscellany
- Currently in the job market for Research Scientist positions; Contributed to the community with a single-file re-implementation of DreamerV3 in JAX, aimed at supporting MBRL research and facilitating the adaptation of the DreamerV3 algorithm.
