Abstract
Deep reinforcement learning (DRL) is increasingly used in application areas such as medicine and finance. However, the direct mapping from state to action in DRL makes it challenging to explain why decisions are made. Existing algorithms for explaining DRL policy are posteriori, explaining to an agent after it has been trained. As a common limitation, these posteriori methods fail to improve training with the deduced knowledge. Face with that, an end-to-end trainable explanation method is proposed, in which an Adaptive Region Scoring Mechanism (ARS) is embedded into DRL system. The ARS explains the agent’s action by evaluating the features of the input state that are most relevant action before DRL re-learn from task-related regions. The proposed method is validated on Atari games. Experiments demonstrate that agent using the explainable proposed mechanism outperforms the original models.
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
Similar content being viewed by others
References
Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870 (2018)
van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 2094–2100 (2016)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928–1937 (2016)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Schulman, J., Moritz, P., Levine, S., Jordan, M.I., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: 4th International Conference on Learning Representations (2016)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Wang, X., Sugumaran, V., Zhang, H., Xu, Z.: A capability assessment model for emergency management organizations. Inf. Syst. Front. 20(4), 653–667 (2018)
Wang, X., Yuan, S., Zhang, H., Lewis, M., Sycara, K.P.: Verbal explanations for deep reinforcement learning neural networks with attention on extracted features. In: 28th IEEE International Conference on Robot and Human Interactive Communication, pp. 1–7 (2019)
Wang, X., Lian, L., Yu, S.X.: Unsupervised visual attention and invariance for reinforcement learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6677–6687 (2021)
Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995–2003 (2016)
Acknowledgement
This work is sponsored by Shanghai Sailing Program (NO. 20YF1413800).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Y., Wang, X., Chang, Y., Jiang, C. (2022). Towards Explainable Reinforcement Learning Using Scoring Mechanism Augmented Agents. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13369. Springer, Cham. https://doi.org/10.1007/978-3-031-10986-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-10986-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10985-0
Online ISBN: 978-3-031-10986-7
eBook Packages: Computer ScienceComputer Science (R0)