Implicit Curriculum in Procgen Made Explicit

Abstract

Procedurally generated environments such as Procgen Benchmark provide a testbed for evaluating the agent's ability to robustly learn a relevant skill, by situating the agent in ever-changing levels. The diverse levels associated with varying contexts are naturally connected to curriculum learning. Existing works mainly focus on arranging the levels to explicitly form a curriculum. In this work, we take a close look at the learning process itself under the multi-level training in Procgen. Interestingly, the learning process exhibits a gradual shift from easy contexts to hard contexts, suggesting an implicit curriculum in multi-level training. Our analysis is made possible through C-Procgen, a benchmark we build upon Procgen that enables explicit control of the contexts. We believe our findings will foster a deeper understanding of learning in diverse contexts, and our benchmark will benefit future research in curriculum reinforcement learning.

Cite

Text

Tan et al. "Implicit Curriculum in Procgen Made Explicit." Neural Information Processing Systems, 2024. doi:10.52202/079017-0646

Markdown

[Tan et al. "Implicit Curriculum in Procgen Made Explicit." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/tan2024neurips-implicit/) doi:10.52202/079017-0646

BibTeX

@inproceedings{tan2024neurips-implicit,
  title     = {{Implicit Curriculum in Procgen Made Explicit}},
  author    = {Tan, Zhenxiong and Wang, Kaixin and Wang, Xinchao},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-0646},
  url       = {https://mlanthology.org/neurips/2024/tan2024neurips-implicit/}
}