Backplay: "Man muss immer umkehren"

Cinjon Resnick
Cinjon Resnick
Sanyam Kapoor
Sanyam Kapoor

arXiv: Learning, Volume abs/1807.06919, 2018.

Cited by: 24|Views35
EI

Abstract:

Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our approach, Backplay, uses a single demonstration to construct a curriculum for a given task. Rather ...More

Code:

Data:

Your rating :
0

 

Tags
Comments