A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning — mentioned by mitchellgoffpc

Fri, 09 Sep 2022 03:36:45 GMT

Some neat results from the last six months or so: - Significantly-improved diffusion models (DALL-E 2, Midjourney, Stable Diffusion, etc) - Diffusion models for video (see https://video-diffusion.github.io/, this paper is from April but I expect to see a lot more published research in this area soon) - OpenAI Minecraft w/VPT (first model with non-zero success rate at mining diamonds in <20min) - AlphaCode (from February, reasonably high success rate on solving competitive programming problems) - Improved realism and scale for NeRFs (see https://dellaert.github.io/NeRF22/ for some cool…

Paper and discussion history. A mention is not an endorsement.

A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning · HackerPapers discussions

A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning — mentioned by mitchellgoffpc