# Atari games and Intel processors

## TL;DR

This paper explores the use of CPU-based asynchronous reinforcement learning algorithms with convolutional neural networks for Atari games, analyzing their convergence and performance using Intel's Math Kernel Library and TensorFlow.

## Contribution

It demonstrates the application of asynchronous RL algorithms with CNNs on CPUs and analyzes their convergence behavior, integrating Intel's MKL and TensorFlow frameworks.

## Key findings

- Asynchronous RL algorithms are well-suited for CPU computations.
- Convolutional neural networks can effectively learn strategies in Atari games.
- Analysis of asynchronous computations impacts on RL convergence.

## 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.