Atari games and Intel processors
This work addresses efficiency in deep reinforcement learning for gaming applications, but it appears incremental as it builds on existing methods like A3C and standard frameworks.
The study tackled the challenge of training reinforcement learning algorithms on Atari games by leveraging asynchronous computations and convolutional neural networks, achieving results that demonstrate improved convergence times, though no specific numerical gains are reported.
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.