Spatial down-sampling techniques, such as strided convolution, Gaussian, and Nearest down-sampling, are essential in deep neural networks.

Modeling dependencies in multivariate discrete data is a challenging problem, especiallyinhighdimensions.

Recently, such difficulty in multi-agent learning has been eased owing to the introduction ofcentralized training for decentralized execution(CTDE) [11, 45], which allows agents to access the global information andopponents' actions during thetraining phase.

Existing works mainly focus on arranging the levels to explicitly form a curriculum. In this work, we take a close look atthelearning process itself under themulti-leveltraining inProcgen.