Abstract
Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach. Here, we consider a benchmark planning problem from the reinforcement learning domain, the Racetrack, to investigate the properties of agents derived from different deep (reinforcement) learning approaches. We compare the performance of deep supervised learning, in particular imitation learning, to reinforcement learning for the Racetrack model. We find that imitation learning yields agents that follow more risky paths. In contrast, the decisions of deep reinforcement learning are more foresighted, i.e., avoid states in which fatal decisions are more likely. Our evaluations show that for this sequential decision making problem, deep reinforcement learning performs best in many aspects even though for imitation learning optimal decisions are considered.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agostinelli, F., McAleer, S., Shmakov, A., Baldi, P.: Solving the Rubik’s Cube with deep reinforcement learning and search. Nat. Mach. Intell. 1(8), 356–363 (2019)
Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to act using real-time dynamic programming. Artif. Intell. 72(1–2), 81–138 (1995)
Bonet, B., Geffner, H.: GPT: a tool for planning with uncertainty and partial information. In: Proceedings of the IJCAI Workshop on Planning with Uncertainty and Incomplete Information, pp. 82–87 (2001)
Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., Steinmetz, M.: Deep statistical model checking. In: Gotsman, A., Sokolova, A. (eds.) FORTE 2020. LNCS, vol. 12136, pp. 96–114. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50086-3_6
Gros, T.P., Höller, D., Hoffmann, J., Wolf, V.: Tracking the race between deep reinforcement learning and imitation learning – extended version. arXiv preprint arXiv:2008.00766 (2020)
Judah, K., Fern, A.P., Dietterich, T.G., Tadepalli, P.: Active imitation learning: formal and practical reductions to I.I.D. learning. J. Mach. Learn. Res. 15(120), 4105–4143 (2014)
Ketkar, N.: Introduction to PyTorch. In: Ketkar, N. (ed.) Deep Learning with Python, pp. 195–208. Apress, Berkeley (2017). https://doi.org/10.1007/978-1-4842-2766-4_12
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Pineda, L.E., Zilberstein, S.: Planning under uncertainty using reduced models: revisiting determinization. In: Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS), pp. 217–225. AAAI Press (2014)
Ross, S., Gordon, G.J., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS). JMLR Proceedings, vol. 15, pp. 627–635. JMLR.org (2011)
Schaal, S.: Is imitation learning the route to humanoid robots? Trends Cogn. Sci. 3(6), 233–242 (1999)
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–503 (2016)
Silver, D., et al.: A general reinforcement learning algorithm that masters Chess, Shogi, and Go through self-play. Science 362(6419), 1140–1144 (2018)
Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550, 354–359 (2017)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning, 2nd edn. The MIT Press, Cambridge (2018)
Acknowledgements
This work has been partially funded by DFG grant 389792660 as part of TRR 248 (see https://perspicuous-computing.science).
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
Gros, T.P., Höller, D., Hoffmann, J., Wolf, V. (2020). Tracking the Race Between Deep Reinforcement Learning and Imitation Learning. In: Gribaudo, M., Jansen, D.N., Remke, A. (eds) Quantitative Evaluation of Systems. QEST 2020. Lecture Notes in Computer Science(), vol 12289. Springer, Cham. https://doi.org/10.1007/978-3-030-59854-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-59854-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59853-2
Online ISBN: 978-3-030-59854-9
eBook Packages: Computer ScienceComputer Science (R0)