One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL

Sergio Gomez Colmenarejo
Sergio Gomez Colmenarejo
Tobias Pfaff
Tobias Pfaff
Gabriel Barth-Maron
Gabriel Barth-Maron
Serkan Cabi
Serkan Cabi

arXiv: Learning, Volume abs/1810.05017, 2018.

Cited by: 10|Bibtex|Views141|Links
EI

Abstract:

Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to...More

Code:

Data:

Your rating :
0

 

Tags
Comments