News for hackers. Stuff that matters.
Re:Deep reinforcement learning is a waste of time (2019) by d4rkp4ttern on Sunday July 11, 2021 @08:50AM (#27800376)
Janner, Li and Levine had a similar, contemporaneous paper —

Reinforcement Learning as One Big Sequence Modeling Problem https://trajectory-transformer.github.io/

There are no comments on this comment yet.