IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
ICML, pp. 1406-1415, 2018.
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
PPT (Upload PPT)