IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Lasse Espeholt
Lasse Espeholt
Tom Ward
Tom Ward
Yotam Doron
Yotam Doron
Vlad Firoiu
Vlad Firoiu

ICML, pp. 1406-1415, 2018.

Cited by: 566|Views280
EI

Abstract:

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time, which is already a problem in single task learning. We have developed a new distributed agent IMPALA (Importance-Weighte...More

Code:

Data:

Your rating :
0

 

Tags
Comments