Curriculum Learning in Reinforcement Learning
Abstract
Transfer learning in reinforcement learning is an area of research that seeks to speed up or improve learning of a complex target task, by leveraging knowledge from one or more source tasks. This thesis will extend the concept of transfer learning to curriculum learning, where the goal is to design a sequence of source tasks for an agent to train on, such that final performance or learning speed is improved. We discuss completed work on this topic, including methods for semi-automatically generating source tasks tailored to an agent and the characteristics of a target domain, and automatically sequencing such tasks into a curriculum. Finally, we also present ideas for future work.
Cite
Text
Narvekar. "Curriculum Learning in Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/757Markdown
[Narvekar. "Curriculum Learning in Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/narvekar2017ijcai-curriculum/) doi:10.24963/IJCAI.2017/757BibTeX
@inproceedings{narvekar2017ijcai-curriculum,
title = {{Curriculum Learning in Reinforcement Learning}},
author = {Narvekar, Sanmit},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {5195-5196},
doi = {10.24963/IJCAI.2017/757},
url = {https://mlanthology.org/ijcai/2017/narvekar2017ijcai-curriculum/}
}