High-Level Goal. Our aim is to devise an agent intrinsically motivated to learn. If the current task is too easy, the agent gets bored; if too hard, it falls into frustration. By maximizing improvement, the agent explores the task space more efficiently and leverages easier task to achieve the learning of a harder one. In other words, we do curriculum learning without explicitly giving a curriculum.
forked from strin/curriculum-deep-RL
txd866/rl-curriculum
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
learning agents with curiosity, with intrinsic motivation to learn increasingly challenging tasks.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- HTML 64.9%
- Python 35.0%
- CSS 0.1%