# MuZero The key idea is that we are *not* trying to predict the entire environment. Rather, we are trying to predict *the minimum information content* that your RL model will need in order to perform well at the task. --- Date: 20230718 Links to: Tags: References: * [MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model - YouTube](https://www.youtube.com/watch?v=We20YSAJZSE)