Hi, I'm Juan

Welcome to my website!



Juan Sebastian Rojas

juan.rojas[at]mail.utoronto.ca

About Me


Hi, I'm Juan! I'm a PhD student at the University of Toronto, where I conduct research as part of the Dynamic Optimization & Reinforcement Learning Lab. My research interests lie in the theory and application of artificial intelligence (AI) in real-world, safety-critical settings. My current research focuses on developing machine learning frameworks and algorithms that incorporate the notions of risk and safety into the learning, planning, and decision-making processes of autonomous agents operating in dynamic, uncertain, and safety-critical environments.


Biography

I hold a degree in engineering with a minor in mathematics from the University of Alberta. I have over five years of experience in industry, where I've contributed to projects that span a broad range of topics, including machine learning, robotics, software engineering, and data science. In my spare time, I enjoy swimming, watching movies, and learning new things.


News

Preprints


October 2025 - Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

Paper

Publications


January 2026 - A Differential Perspective on Distributional Reinforcement Learning

AAAI Conference on Artificial Intelligence (AAAI-26)

Paper


August 2025 - Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes

Reinforcement Learning Journal

Paper Code


September 2022 - Comparison of Machine Learning Models for Quantitative Risk Modelling of Pipeline Systems

ASME International Pipeline Conference

Paper


September 2022 - Subset Simulation of Pipeline Corrosion, Crack, and Dent Defects Considering Multiple Limit States With Large-Scale Validation

ASME International Pipeline Conference

Paper

Talks


February 2019 - LQR Control of an Autonomous Underwater Vehicle

MATLAB and Simulink Robotics Arena

Video Code