In my free time, I lead maintenance of Gymnasium & Gym, the standard APIs powering RL research worldwide, and am a core team member at the Farama Foundation. I further contribute to a range of open-source mostly RL related software.
In 2025, I completed my PhD in Explainable RL at the University of Southampton, resulting in numerous published papers on explaining agents' decision-making, with a selection listed below.
Selected Projects
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym).
A platform for AI research using Atari 2600 games as benchmarks for reinforcement learning algorithms.
An API for JAX-based Reinforcement Learning Environments.
A suite of RL training algorithms written purely in JAX to enable end-to-end JIT and vmapping.
Selected Publications
For a complete list, see my Google Scholar profile.
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
- Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators
- A Comparative User Evaluation of XRL Explanations using Goal Identification
- Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
- Beyond the Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC
- Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning