How Transferable are the Representations Learned by Deep Q Agents?

Tyo Jacob
Tyo Jacob
Cited by: 0|Views31

Abstract:

In this paper, we consider the source of Deep Reinforcement Learning (DRL)'s sample complexity, asking how much derives from the requirement of learning useful representations of environment states and how much is due to the sample complexity of learning a policy. While for DRL agents, the distinction between representation and policy m...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments