Mark Bedaywi

Hello! I’m Mark Bedaywi, a first year Computer Science PhD student at Berkeley AI Research in UC Berkeley, working on AI safety and EconML, advised by Nika Haghtalab and Stuart Russell.

I’ve done work on fairly aggregating preferences in multi-agent systems, accelerating reinforcement learning algorithms, and identifying safety failure modes for AI assistants. My current interests include collaborative learning between agents, inverse reinforcement learning and assistance games, and the game theory of persuasion, agreement, and cooperation.