PinnedWe need a new learning theory for embodied AIThis is an extended section from our Embodied AI ICML24 paper with Giuseppe Paolo and Jonas GonzalezSep 25Sep 25
PinnedThe case for aligning the AI scientistPut on your oxygen mask first, before helping othersMay 6, 2023May 6, 2023
Navigating the maze of hyperparameter optimization: insights from a systematic studySummary of my preprint https://arxiv.org/abs/2311.15854Dec 2, 2023Dec 2, 2023
Mind everywhere, embodied AI of things, and the future of engineeringHow will the next generation of systems look like?Nov 13, 2023Nov 13, 2023
GPT-4 in conversation with itselfFrom batshit crazy to informative but not yet humanMay 18, 2023May 18, 2023
I think this is a fantastic read, thank you, Vincent, I'm using it in our experiments as we speak.Apr 29, 2021Apr 29, 2021
Building autopilots for engineering systems using AIIterated offline reinforcement learning and contextual bandits: motivations and research themesDec 18, 2020Dec 18, 2020
Published inTowards Data ScienceModel-based micro-data reinforcement learning:What are the crucial model properties and which model to choose?Dec 9, 2020Dec 9, 2020