Skip to main content

Hierarchical Actor-Critic with Hindsight for Mobile Robot with Continuous State Space

Part of the Studies in Computational Intelligence book series (SCI,volume 856)

Abstract

Hierarchies are used in reinforcement learning to increase learning speed in sparse reward tasks. In this kind of tasks, the main problem is elapsed time, required for the initial policy to reach the goal during the first steps. Hierarchies can split a problem into a set of subproblems that could be reached in less time. In order to implement this idea, Hierarchical Reinforcement Learning (HRL) algorithms need to be able to learn the multiple levels within a hierarchy in parallel, so these smaller subproblems could be solved at the same time. Most famous existing HRL algorithms that can learn multi-level hierarchies are not able to efficiently learn levels of policies simultaneously, especially in continuous space and action space environment. To address this problem, we had analyzed the newest existing framework, Hierarchical Actor-Critic with Hindsight (HAC), test it in the simulated mobile robot environment and determine the optimal configuration of parameters and ways to encode information about the environment states.

Keywords

  • Hierarchical Actor-Critic
  • Hindsight Experience Replay
  • Reinforcement learning

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-30425-6_6
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   129.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-30425-6
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   169.99
Price excludes VAT (USA)
Hardcover Book
USD   249.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.

References

  1. Schmidhuber, J.: Learning to generate sub-goals for action sequences. In: Kohonen, T., Mäkisara, K., Simula, O., Kangas, J. (eds.) Artificial Neural Networks, pp. 967–972. Elsevier Science Publishers B.V., North-Holland (1991)

    Google Scholar 

  2. Konidaris, G.D., Barto, A.G.: Skill discovery in continuous reinforcement learning domains using skill chaining. Adv. Neural. Inf. Process. Syst. 22, 1015–1023 (2009)

    Google Scholar 

  3. Bacon, P.-L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 1726–1734 (2017)

    Google Scholar 

  4. Vezhnevets, A., Osindero, S., Schaul, T., Heess, N., Jaderberg, M., Silver, D., Kavukcuoglu, K.: FeUdal networks for hierarchical reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, pp. 3540–3549 (2017)

    Google Scholar 

  5. Nachum, O., Gu, S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. Adv. Neural. Inf. Process. Syst. 31, 3303–3313 (2018)

    Google Scholar 

  6. Levy, A., Konidaris, G., Platt, R., Saenko, K.: Learning multi-level hierarchies with hindsight. arXiv:1712.00948. [cs.AI], March 2019

  7. Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B., Tobin, J., Abbeel, P., Zaremba, W.: Hindsight experience replay. Adv. Neural. Inf. Process. Syst. 30, 5048–5058 (2017)

    Google Scholar 

  8. Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. CoRR (2015). arXiv:1509.02971

  9. Silver, D., Schaul, T., Horgan, D., Gregor, K.: Universal value function approximators. In: International Conference on Machine Learning (July 2015)

    Google Scholar 

  10. Shikunov, M., Panov, A.I.: Hierarchical reinforcement learning approach for the road intersection task. In: Samsonovich, A.V. (ed.) Biologically Inspired Cognitive Architectures 2019. Springer, Cham (2019)

    Google Scholar 

  11. Kuzmin, V., Panov, A.I.: Hierarchical reinforcement learning with options and united neural network approximation. In: Abraham, A., Kovalev, S., Tarassov, V., Snasel, V., Sukhanov, A. (eds.) Proceedings of the Third International Scientific Conference “Intelligent Information Technologies for Industry” (IITI 2018), pp. 453–462. Springer, Cham (2018)

    Google Scholar 

  12. Ayunts, E., Panov, A.I.: Task planning in “Block World” with deep reinforcement learning. In: Samsonovich, A.V., Klimov, V.V. (eds.) Biologically Inspired Cognitive Architectures (BICA) for Young Scientists, pp. 3–9. Springer, Cham (2017)

    Google Scholar 

Download references

Acknowledgements

The reported study was supported by RFBR, research Projects No. 17-29-07079.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Aleksandr I. Panov .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Aleksey, S., Panov, A.I. (2020). Hierarchical Actor-Critic with Hindsight for Mobile Robot with Continuous State Space. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research III. NEUROINFORMATICS 2019. Studies in Computational Intelligence, vol 856. Springer, Cham. https://doi.org/10.1007/978-3-030-30425-6_6

Download citation