Efficient Parallel Methods for Deep Reinforcement Learning
Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, Norway
arXiv:1705.04862 [cs.LG], (16 May 2017)
@article{clemente2017efficient,
title={Efficient Parallel Methods for Deep Reinforcement Learning},
author={Clemente, Alfredo V. and Castejon, Humberto N. and Chandra, Arjun},
year={2017},
month={may},
archivePrefix={"arXiv"},
primaryClass={cs.LG}
}
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-policy experiences and employing synchronous updates. Our algorithm achieves state-of-the-art performance on the Atari domain after only a few hours of training. Our framework thus opens the door for much faster experimentation on demanding problem domains. Our implementation is open-source.
May 18, 2017 by hgpu
