Skip to main content

Delta Schema Network in Model-Based Reinforcement Learning

Part of the Lecture Notes in Computer Science book series (LNAI,volume 12177)


This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.


  • Reinforcement learning
  • Model-based
  • Schema Network
  • Delta Schema Network
  • Transfer learning

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

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-52152-3_18
  • Chapter length: 11 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   79.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-52152-3
  • 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   99.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.


  1. Attias, H.: Planning by probabilistic inference. In: AISTATS. Citeseer (2003)

    Google Scholar 

  2. Badreddine, S., Spranger, M.: Injecting prior knowledge for transfer learning into reinforcement learning algorithms using logic tensor networks. arXiv preprint arXiv:1906.06576 (2019)

  3. Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Advances in Neural Information Processing Systems, pp. 4502–4510 (2016)

    Google Scholar 

  4. Diuk, C., Cohen, A., Littman, M.L.: An object-oriented representation for efficient reinforcement learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 240–247 (2008)

    Google Scholar 

  5. Kansky, K., et al.: Schema networks: zero-shot transfer with a generative causal model of intuitive physics. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1809–1818. (2017)

    Google Scholar 

  6. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)

  7. Kiselev, G., Panov, A.: Hierarchical psychologically inspired planning for human-robot interaction tasks. In: Ronzhin, A., Rigoll, G., Meshcheryakov, R. (eds.) ICR 2019. LNCS (LNAI), vol. 11659, pp. 150–160. Springer, Cham (2019).

    CrossRef  Google Scholar 

  8. Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)

    CrossRef  Google Scholar 

  9. Panov, A.I., Yakovlev, K.S.: Psychologically inspired planning method for smart relocation task. Procedia Comput. Sci. 88, 115–124 (2016).

    CrossRef  Google Scholar 

  10. Serafini, L., Garcez, A.d.: Logic tensor networks: deep learning and logical reasoning from data and knowledge. arXiv preprint arXiv:1606.04422 (2016)

  11. Shikunov, M., Panov, A.I.: Hierarchical reinforcement learning approach for the road intersection task. In: Samsonovich, A.V. (ed.) BICA 2019. AISC, vol. 948, pp. 495–506. Springer, Cham (2020).

    CrossRef  Google Scholar 

  12. Smirnov, I., Panov, A.I., Skrynnik, A., Isakov, V., Chistova, E.: Personal cognitive assistant: concept and key principals. Informatika i ee Primeneniya 13(3), 105–113 (2019).

    CrossRef  Google Scholar 

  13. Toyer, S., Trevizan, F., Thiébaux, S., Xie, L.: Action schema networks: generalised policies with deep learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  14. Younes, A., Panov, A.I.: Toward faster reinforcement learning for robotics: using Gaussian processes. In: Osipov, G.S., Panov, A.I., Yakovlev, K.S. (eds.) Artificial Intelligence. LNCS (LNAI), vol. 11866, pp. 160–174. Springer, Cham (2019).

    CrossRef  Google Scholar 

Download references


The reported study was partially supported by RFBR, research Projects No. 17-29-07079 and No. 18-29-22027.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Aleksandr I. Panov .

Editor information

Editors and Affiliations

A Appendix

A Appendix

Algorithms 1 and 2 are used in Algorithm 3. Node in the graph is considered to have next attributes:

figure a
figure b
figure c
  • node.is_reachable - the actual reachability of the node, subject to currently selected actions, or \(\texttt {None}\) if the reachability is not known.

  • node.schemas - map from actions to node’s schemas requiring these actions

  • node.transition - self-transition node, if any

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

Gorodetskiy, A., Shlychkova, A., Panov, A.I. (2020). Delta Schema Network in Model-Based Reinforcement Learning. In: Goertzel, B., Panov, A., Potapov, A., Yampolskiy, R. (eds) Artificial General Intelligence. AGI 2020. Lecture Notes in Computer Science(), vol 12177. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-52151-6

  • Online ISBN: 978-3-030-52152-3

  • eBook Packages: Computer ScienceComputer Science (R0)