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

First published at 13:23 UTC on November 1st, 2019.
subscribers

Policy Gradient RL on a massively distributed scale with theoretical guarantees!

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 ha…

MORE
CategoryScience & Technology
SensitivityNormal - Content that is suitable for ages 16 and over
DISCUSS THIS VIDEO