Mark Towers

Hi, I'm Mark

Reinforcement Learning Engineer with a PhD in Explainable RL

Currently, I'm a Software Engineer at Anyscale, developing RLlib allowing engineers to scale reinforcement learning training from 1 to 64 GPUs for real-world problems.

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

Selected Publications

For a complete list, see my Google Scholar profile.