Deep Reinforcement Learning: An Overview

  • Seyed Sajad MousaviEmail author
  • Michael Schukat
  • Enda Howley
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 16)


In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This article reviews the recent advances in deep reinforcement learning with focus on the most used deep architectures such as autoencoders, convolutional neural networks and recurrent neural networks which have successfully been come together with the reinforcement learning framework.


Reinforcement learning Deep leaning Neural networks MDPs Observable MDPs 


  1. 1.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  2. 2.
    Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32, 1238–1274 (2013)CrossRefGoogle Scholar
  3. 3.
    Vengerov, D.: A reinforcement learning approach to dynamic resource allocation. Sun Microsystems, Inc. (2005)Google Scholar
  4. 4.
    Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete Event Dyn. Syst. 13, 341–379 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Mousavi, S.S., Ghazanfari, B., Mozayani, N., Jahed-Motlagh, M.R.: Automatic abstraction controller in reinforcement learning agent via automata. Appl. Soft Comput. 25, 118–128 (2014)CrossRefGoogle Scholar
  6. 6.
    Sutton, R.S., David, A.M., Satinder, P.S., Mansour, Y.: Policy Gradient Methods for Reinforcement Learning with Function Approximation, pp. 1057–1063 (2000)Google Scholar
  7. 7.
    Mattner, J., Lange, S., Riedmiller, M.: Learn to swing up and balance a real pole based on raw visual input data. In: Huang, T., Zeng, Z., Li, C., Leung, C.S., (eds.) Neural Information Processing: 19th International Conference, ICONIP 2012, Doha, Qatar, 12–15 November 2012, Proceedings, Part V, pp. 126–133. Springer, Heidelberg (2012)Google Scholar
  8. 8.
    Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., et al.: Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)Google Scholar
  9. 9.
    Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)CrossRefGoogle Scholar
  10. 10.
    Böhmer, W., Springenberg, J.T., Boedecker, J., Riedmiller, M., Obermayer, K.: Autonomous learning of state representations for control: an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations. KI - Künstliche Intelligenz 29, 353–362 (2015)CrossRefGoogle Scholar
  11. 11.
    Levine, S., Fin, C., Darre, T., Abbee, P.: End-to-End training of deep visuomotor policies. arXiv:1504.00702 (2015)
  12. 12.
    Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. (JAIR) 4, 237–285 (1996)Google Scholar
  13. 13.
    Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)Google Scholar
  14. 14.
    Riedmiller, M.: Neural fitted Q iteration – first experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L., (eds.) Machine Learning: ECML 2005: 16th European Conference on Machine Learning, Porto, Portugal, 3–7 October 2005, Proceedings, pp. 317–328. Springer, Heidelberg (2005)Google Scholar
  15. 15.
    Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in Atari games, pp. 2845–2853 (2015)Google Scholar
  16. 16.
    Bengio, Y.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798–1828 (2013)CrossRefGoogle Scholar
  17. 17.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2009)CrossRefzbMATHGoogle Scholar
  18. 18.
    Bengio, Y., Pascal, L., Dan, P., Larochelle, H.: Greedy Layer-Wise Training of Deep Networks, pp. 153–160 (2007)Google Scholar
  19. 19.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A.: Extracting and composing robust features with denoising autoencoders. Presented at the Proceedings of the 25th International Conference on Machine learning, Helsinki, Finland (2008)Google Scholar
  20. 20.
    Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)MathSciNetzbMATHGoogle Scholar
  21. 21.
    LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989)CrossRefGoogle Scholar
  22. 22.
    LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: Michael, A.A., (ed.) The Handbook of Brain Theory and Neural Networks, pp. 255–258. MIT Press (1998)Google Scholar
  23. 23.
    Scherer, D., Müller, A., Behnke, S.: Evaluation of pooling operations in convolutional architectures for object recognition. In: Diamantaras, K., Duch, W., Iliadis, L.S., (eds.) Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, 15–18 September 2010, Proceedings, Part III, pp. 92–101. Springer, Heidelberg (2010)Google Scholar
  24. 24.
    Deng, J., Dong, W., Socher, R., Li, L.J., Kai, L., Li, F.-F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009, pp. 248–255 (2009)Google Scholar
  25. 25.
    Deng, L., Hinton, G., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8599–8603 (2013)Google Scholar
  26. 26.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5, 157–166 (1994)CrossRefGoogle Scholar
  27. 27.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  28. 28.
    Tesauro, G.: TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6, 215–219 (1994)CrossRefGoogle Scholar
  29. 29.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE International Conference on Neural Networks, 1993, vol. 1, pp. 586–591 (1993)Google Scholar
  30. 30.
    Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Int. Res. 47, 253–279 (2013)Google Scholar
  31. 31.
    Lin, L.-J.: Reinforcement learning for robots using neural networks. Carnegie Mellon University (1993)Google Scholar
  32. 32.
    Guo, X., Singh, S., Lee, H., Lewis, R.L., Wang, X.: Deep learning for real-time atari game play using offline monte-carlo tree search planning, pp. 3338–3346 (2014)Google Scholar
  33. 33.
    Kocsis, L., Szepesvári, C.: Bandit based monte-carlo planning. Presented at the Proceedings of the 17th European Conference on Machine Learning, Berlin, Germany (2006)Google Scholar
  34. 34.
    Grüttner, M., Sehnke, F., Schaul, T., Schmidhuber, J.: Multi-dimensional deep memory Atari-Go players for parameter exploring policy gradients. In: Diamantaras, K., Duch, W., Iliadis, L.S., (eds.) Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, 15–18 September 2010, Proceedings, Part II, pp. 114–123. Springer, Heidelberg (2010)Google Scholar
  35. 35.
    Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F., (eds.) A Field Guide to Dynamical Recurrent Neural Networks (2001)Google Scholar
  36. 36.
    Sehnke, F., Osendorfer, C., Rückstieß, T., Graves, A., Peters, J., Schmidhuber, J.: Parameter-exploring policy gradients. Neural Netw. 23(4), 551–559 (2010)CrossRefGoogle Scholar
  37. 37.
    Beyer, H.-G., Schwefel, H.-P.: Evolution strategies – a comprehensive introduction. Nat. Comput. 1, 3–52 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  38. 38.
    Clark, C., Storkey, A.: Teaching deep convolutional neural networks to play Go, arXiv preprint arXiv:1412.3409 (2014)
  39. 39.
    Koutní, J., Cuccu, G., Schmidhuber, J., Gomez, F.: Evolving large-scale neural networks for vision-based reinforcement learning. In: Proceedings of the Genetic and Evolutionary Computation Conference, Amsterdam, pp. 1061–1068 (2013)Google Scholar
  40. 40.
    Lange, S., Riedmiller, M.: Deep auto-encoder neural networks in reinforcement learning. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2010)Google Scholar
  41. 41.
    Lange, S., Riedmiller, M., Voigtlaender, A.: Autonomous reinforcement learning on raw visual input data in a real world application. In: International Joint Conference on Neural Networks, pp. 1–8 (2012)Google Scholar
  42. 42.
    Ormoneit, D., Sen, Ś.: Kernel-based reinforcement learning. Mach. Learn. 49, 161–178 (2002)CrossRefzbMATHGoogle Scholar
  43. 43.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  44. 44.
    Bakker, B., Zhumatiy, V., Gruener, G., Schmidhuber, J.: A robot that reinforcement-learns to identify and memorize important previous observations. In: 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2003, (IROS 2003), Proceedings, vol. 1, pp. 430–435 (2003)Google Scholar
  45. 45.
    Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs, arXiv preprint arXiv:1507.06527v3 (2015)

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Seyed Sajad Mousavi
    • 1
    Email author
  • Michael Schukat
    • 1
  • Enda Howley
    • 1
  1. 1.The College of Engineering and InformaticsNational University of IrelandGalwayRepublic of Ireland

Personalised recommendations