← Search

Philippe Hamel

2 accepted papers

2019

The Option Keyboard: Combining Skills in Reinforcement Learning

NeurIPS 2019poster

The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or "cumulants"). Based o…

Cited by 122SourcePDFScholar