English

Atari games and Intel processors

Distributed, Parallel, and Cluster Computing 2018-04-17 v1 Artificial Intelligence Machine Learning

Abstract

The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep reinforcement learning often deals with interpreting visual information, a large part of the train and inference time is spent performing convolutions. In this work we present our results on learning strategies in Atari games using a Convolutional Neural Network, the Math Kernel Library and TensorFlow 0.11rc0 machine learning framework. We also analyze effects of asynchronous computations on the convergence of reinforcement learning algorithms.

Keywords

Cite

@article{arxiv.1705.06936,
  title  = {Atari games and Intel processors},
  author = {Robert Adamski and Tomasz Grel and Maciej Klimek and Henryk Michalewski},
  journal= {arXiv preprint arXiv:1705.06936},
  year   = {2018}
}