Abstract
Deep Reinforcement learning (DRL) algorithms recently still take a long time to train models in many applications. Parallelization has the potential to improve the efficiency of DRL algorithms. In this paper, we propose an parallel approach (ParaA2C) for the popular Actor-Critic (AC) algorithms in DRL, to accelerate the training process. Our work considers the parallelization of the basic advantage actor critic (Serial-A2C) in AC algorithms. Specifically, we use multiple actor-learners to mitigate the strong correlation of data and the instability of updating, and finally reduce the training time. Note that we assign each actor-learner MPI process to a CPU core, in order to prevent resource contention between MPI processes, and make our ParaA2C approach more scalable. We demonstrate the effectiveness of ParaA2C by performing on Arcade Learning Environment (ALE) platform. Notably, our ParaA2C approach takes less than 10 min to train in some commonly used Atari games when using 512 CPU cores.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adamski, I., Adamski, R., Grel, T., Jędrych, A., Kaczmarek, K., Michalewski, H.: Distributed deep reinforcement learning: learn how to play atari games in 21 minutes. In: Yokota, R., Weiland, M., Keyes, D., Trinitis, C. (eds.) ISC High Performance 2018. LNCS, vol. 10876, pp. 370–388. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-92040-5_19
Adamski, R., Grel, T., Klimek, M., Michalewski, H.: Atari games and intel processors. In: Cazenave, T., Winands, M.H.M., Saffidine, A. (eds.) CGW 2017. CCIS, vol. 818, pp. 1–18. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75931-9_1
Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., Kautz, J.: Reinforcement learning through asynchronous advantage actor-critic on a GPU. arXiv preprint arXiv:1611.06256 (2016)
Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–279 (2013)
Clemente, A.V., Castejón, H.N., Chandra, A.: Efficient parallel methods for deep reinforcement learning. arXiv preprint arXiv:1705.04862 (2017)
Dhariwal, P., et al.: Openai baselines (2017). https://github.com/openai/baselines
Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008–1014 (2000)
Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997 (2014)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928–1937 (2016)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Stooke, A., Abbeel, P.: Accelerated methods for deep reinforcement learning. arXiv preprint arXiv:1803.02811 (2018)
Acknowledgements
This research was supported by the Natural Science Foundation of China under Grant NO. U1811464 and the Program for Guangdong Introducing Innovative and Enterpreneurial Teams under Grant NO. 2016ZT06D211.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, X., Du, Y. (2020). A Parallel Approach to Advantage Actor Critic in Deep Reinforcement Learning. In: Wen, S., Zomaya, A., Yang, L.T. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2019. Lecture Notes in Computer Science(), vol 11945. Springer, Cham. https://doi.org/10.1007/978-3-030-38961-1_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-38961-1_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38960-4
Online ISBN: 978-3-030-38961-1
eBook Packages: Computer ScienceComputer Science (R0)