dsep/vectorizedmultiagentsimulator

VMAS is a vectorized framework designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

Hey, I'm Sepand! 👋

🔭 I'm a co-founder of a startup building software and machine learning models to enable sustainable fisheries (OnDeck). I recently finished my time as a Master's student in Computer Science at Cambridge. Overall, I'm passionate about tech, space, and working on interesting problems!

🌱 Previously, I completed my Bachelor's of Science in Computer Science at the University of British Columbia (UBC). Concurrently, I was a research intern at Polytechnique Montréal, working on a robotic swarms project (think bee or ant-like autonomous coordination). For two summers, I was also an SDE intern at Amazon with the Amazon Fuse team. Prior to that, I was an intern at the European Space Agency, specifically on the CAVES and PANGAEA team at the European Astronaut Centre.

⚡ I'm always interested in new projects and interesting discussions. Feel free to get in touch through LinkedIn or my website.