Bibliography (6):

1. Agent57: Outperforming the Atari Human Benchmark

2. Muesli: Combining Improvements in Policy Optimization

3. MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

4. NFNet: High-Performance Large-Scale Image Recognition Without Normalization

5. Wikipedia Bibliography:

   1. Reinforcement learning

   2. https://en.wikipedia.org/wiki/Trust_region  :

      https://en.wikipedia.org/wiki/Trust_region