NeurIPS 2024 - Posters and Hallways 1
TalkRL: The Reinforcement Learning Podcast
00:00
Intro
This chapter explores a new method for unsupervised skills discovery in hierarchical reinforcement learning, addressing the difficulties of skill selection in specific states without explicit rewards. Through a practical example of driving a car, it demonstrates how a structured skill space can improve performance in various tasks.
Transcript
Play full episode
