[New post] A Benchmark for Learning from Human Feedback – The Berkeley Artificial Intelligence Research Blog

Matteo posted: " TL;DR: We are launching a NeurIPS competition and benchmark called BASALT: a set of Minecraft environments and a human evaluation protocol that we hope will stimulate research and investigation into solving tasks with no pre-specifie" New post on Matteo Sala A Benchmark for Learning from Human Feedback – The Berkeley Artificial Intelligence Research Blog by Matteo TL;DR: We are launching a NeurIPS competition and benchmark called BASALT: a set of Minecraft environments and a human evaluation protocol that we hope will stimulate research and investigation into solving tasks with no pre-specified reward function, where the goal of an agent must be communicated through demonstrations, preferences, or some other form of human feedback. Sign up to participate in the competition! Continue reading "A Benchmark for Learning from Human Feedback – The Berkeley Artificial Intelligence Research Blog" Matteo | September 18, 2021 at 6:14 am | Tags: Artificial, Benchmark, Berkeley, Blog, Feedback, Human, intelligence, learning, research | Categories: Artificial Intelligence | URL: https://wp.me/pcAtNR-30Y Comment    See all comments Unsubscribe to no longer receive posts from Matteo Sala. Change your email settings at Manage Subscriptions. Trouble clicking? Copy and paste this URL into your browser: https://salamatteo.com/2021/09/18/a-benchmark-for-learning-from-human-feedback-the-berkeley-artificial-intelligence-research-blog/