We formulate the curriculum transfer problem, in which the schema of a curriculum optimized in a simpler, easy-to-solve environment (e.g., a grid world) is transferred to a complex, realistic scenario (e.g., a physics-based robotics simulation or the real world). We present "ACuTE", Automatic Curriculum Transfer from Simple to Complex Environments, a novel framework to solve this problem, and evaluate our proposed method by comparing it to other baseline approaches (e.g., domain adaptation) designed to speed up learning.
@article{shuklaetal2022aamas, title={ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments}, author={Yash Shukla and Christopher Thierauf and Ramtin Hosseini and Gyan Tatiya and Jivko Sinapov}, year={2022}, journal={AAMAS}, url={https://hrilab.tufts.edu/publications/shuklaetal2022aamas.pdf} }