Skip to main content

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning and Snapshot Ensembling

  • Conference paper
  • First Online:
Intelligent Systems and Applications (IntelliSys 2018)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 868))

Included in the following conference series:

Abstract

ViZDoom is a robust, first-person shooter reinforcement learning environment, characterized by a significant degree of latent state information. In this paper, double-Q learning and prioritized experience replay methods are tested under a certain ViZDoom combat scenario using a competitive deep recurrent Q-network (DRQN) architecture. In addition, an ensembling technique known as snapshot ensembling is employed using a specific annealed learning rate to observe differences in ensembling efficacy under these two methods. Annealed learning rates are important in general to the training of deep neural network models, as they shake up the status-quo and counter a model’s tending towards local optima. While both variants show performance exceeding those of built-in AI agents of the game, the known stabilizing effects of double-Q learning are illustrated, and priority experience replay is again validated in its usefulness by showing immediate results early on in agent development, with the caveat that value overestimation is accelerated in this case. In addition, some unique behaviors are observed to develop for priority experience replay (PER) and double-Q (DDQ) variants, and snapshot ensembling of both PER and DDQ proves a valuable method for improving performance of the ViZDoom Marine.

This work was not supported by any organization.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Braylan, A., Hollenbeck, M., Meyerson, E., Miikkulainen, R.: Frame skip is a powerful parameter for learning to play Atari. Space 1600, 1800 (2005)

    Google Scholar 

  2. Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. (2012)

    Google Scholar 

  3. Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge England (1989)

    Google Scholar 

  4. Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E., Weinberger, K.Q.: Snapshot ensembles: Train 1, get M for free. ICLR submission (2017)

    Google Scholar 

  5. Lample, G., Chaplot, D.S.: Playing FPS games with deep reinforcement learning. arXiv preprint arXiv:1609.05521 (2016)

  6. Hasselt, H.V.: Double q-learning. In: Advances in Neural Information Processing Systems, pp. 2613–2621 (2010)

    Google Scholar 

  7. Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable MDPS. arXiv preprint arXiv:1507.06527 (2015)

  8. Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jakowski, W.: Vizdoom: a doom-based AI research platform for visual reinforcement learning. In: IEEE Conference on Computational Intelligence and Games (2016)

    Google Scholar 

  9. Justensen, N., Bontrager, P., Togelius, J., Risi, S.: Deep Learning for Video Game Playing. ArXiv:1708.07902

  10. Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)

    Google Scholar 

  11. Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3(1), 9–44 (1988)

    Google Scholar 

  12. Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: International Conference on Learning Representations (ICLR). http://arxiv.org/abs/1511.05952 (2016)

  13. Dozat, T.: Incorporating Nesterov momentum into Adam. Technical Report, Stanford University (2015). http://cs229.stanford.edu/proj2015/054_report.pdf

  14. Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. arXiv preprint arXiv:1509.06461 (2015)

Download references

Acknowledgment

The authors here would like to thank: (1) the ViZDoom development team for their continued maintenance and extension of this remarkable RL framework, and (2) IEEE CIG for their support of the annual ViZDoom Limited and Full Deathmatch Competitions.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Christopher Schulze .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Schulze, C., Schulze, M. (2019). ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning and Snapshot Ensembling. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Systems and Applications. IntelliSys 2018. Advances in Intelligent Systems and Computing, vol 868. Springer, Cham. https://doi.org/10.1007/978-3-030-01054-6_1

Download citation

Publish with us

Policies and ethics