New #RLC2024 paper Three Dogmas of Reinforcement Learning joint w/ Mark Ho and Anna Harutyunyan | Աննա Հարությունյան! arxiv.org/pdf/2407.10583 We reflect on where our scientific paradigm needs adjustment, and suggest three departures from previous conventions. Curious to hear what folks think! 🧵

The PhD apprenticeship is so exciting because there is no silver bullet. All young researchers must discover a set of research strategies that best accelerate their work. In doing so, everyone acquires their own unique perspective on their field and academia as a whole.

We’re releasing Humanity’s Last Exam, a dataset with 3,000 questions developed with hundreds of subject matter experts to capture the human frontier of knowledge and reasoning. State-of-the-art AIs get <10% accuracy and are highly overconfident. pak.ai Scale.ai

Disappointed with your ICLR paper being rejected? Ten years ago today, Sergey and I finished training some of the first end-to-end neutral nets for robot control 🤖 We submitted the paper to RSS on January 23, 2015. It was rejected for being "incremental" and "unlikely to have

Shared autonomy systems have been around for a long time but most approaches require a learned or specified set of possible human goals or intents. I'm excited for my student Connor Mattson to present our work at #HRI2025 on a zero-shot, vision-only shared autonomy (VOSA) framework.