Abstract
Deep reinforcement learning (DRL) has been widely employed in game industry, mainly for building automatic game agents. While its performance and efficiency has significantly outperformed traditional approaches, the lack of model transparency constrains the interaction between the model and the human operators, thus degrading the practicality of DRL methods. In this paper, we propose to mitigate this human-AI interaction issue in a game industry scenario. Previously, existing methods need repetitive execution of DRL or are designed towards specific tasks, which are not applicable for our deployment scenario. Considering that different games could have different DRL AI agents, we hereby develop a post-hoc explanation framework which regards original DRL as a black-box model and can be applicable to any DRL based agents. Within the framework, a specially selected student model, which has been already well explored for model explanation, is employed to learn the decision policies of the trained DRL model. Then, by giving explanation information for the student model, indirect but practical explanation results can be obtained for original DRL model. Based on this information, the interaction between human and AI agents can be enhanced, benefiting deployment of DRL. Finally, based on the dataset from a real-world production game, we conduct experiments and user studies to illustrate the effectiveness of the proposed procedure from both objective and subjective perspectives.
Similar content being viewed by others
Data Availability
The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Agius H, Daylamani-Zad D (2021) Guest editorial: interaction in immersive experiences. Multimed Tools Appl 80(20):30939–30942
Amershi S, Fogarty J, Weld D (2012) Regroup: Interactive machine learning for on-demand group creation in social networks. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 21–30
Amir D, Amir O (2018) Highlights: summarizing agent behavior to people. In: Proceedings of the 17th international conference on autonomous agents and multiagent systems, pp 1168–1176
Anderson A, Dodge J, Sadarangani A et al (2019) Explaining reinforcement learning to mere mortals: an empirical study. In: Proceedings of the 28th international joint conference on artificial intelligence, pp 1328–1334
Arrieta A B, Díaz-rodríguez N, Del Ser J et al (2020) Explainable artificial intelligence (xai): concepts, taxonomies, opportunities and challenges toward responsible ai. Inf Fusion 58:82–115
Arulkumaran K, Deisenroth M P, Brundage M et al (2017) Deep reinforcement learning: a brief survey. IEEE Signal Proc Mag 34(6):26–38
Berner C, Brockman G, Chan B et al (2019) Dota 2 with large scale deep reinforcement learning. arXiv:191206680
Bhatt U, Xiang A, Sharma S et al (2020) Explainable machine learning in deployment. In: Proceedings of the 2020 conference on fairness, accountability, and transparency, pp 648–657
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Carmigniani J, Furht B, Anisetti M et al (2011) Augmented reality technologies, systems and applications. Multimed Tools Appl 51(1):341–377
Checa D, Bustillo A (2020) A review of immersive virtual reality serious games to enhance learning and training. Multimed Tools Appl 79(9):5501–5527
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785–794
Fails J A, Olsen D R Jr (2003) Interactive machine learning. In: Proceedings of the 8th international conference on intelligent user interfaces, pp 39–45
Frid E, Gomes C, Jin Z (2020) Music creation by example. In: Proceedings of the 2020 CHI conference on human factors in computing systems, pp 1–13
Ghorbani A, Wexler J, Zou J Y et al (2019) Towards automatic concept-based explanations. In: Advances in neural information processing systems, p 32
Gillies M, Fiebrink R, Tanaka A et al (2016) Human-centred machine learning. In: Proceedings of the 2016 CHI conference extended abstracts on human factors in computing systems, CHI EA ’16. Association for Computing Machinery, New York, pp 3558–3565. https://doi.org/10.1145/2851581.2856492
Greydanus S, Koul A, Dodge J et al (2018) Visualizing and understanding atari agents. In: International conference on machine learning, PMLR, pp 1792–1801
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Heuillet A, Couthouis F, Díaz-Rodríguez N (2021) Explainability in deep reinforcement learning. Knowl-Based Syst 214:106,685. https://doi.org/10.1016/j.knosys.2020.106685. https://www.sciencedirect.com/science/article/pii/S0950705120308145
Juozapaitis Z, Koul A, Fern A et al (2019) Explainable reinforcement learning via reward decomposition. In: Proceedings at the international joint conference on artificial intelligence. A workshop on explainable artificial intelligence
Ke G, Meng Q, Finley T et al (2017) Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, p 30
Kuhn HW, Tucker AW (1953) Contributions to the theory of games, vol 2. Princeton University Press
Kulesza T, Amershi S, Caruana R et al (2014) Structured labeling for facilitating concept evolution in machine learning. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 3075–3084
Lage I, Ross A, Gershman S J et al (2018) Human-in-the-loop interpretability prior. In: Advances in neural information processing systems, p 31
Laugwitz B, Held T, Schrepp M (2008) Construction and evaluation of a user experience questionnaire. In: Symposium of the austrian HCI and usability engineering group, springer, pp 63–76
Lee LH, Braud T, Zhou P et al (2021) All one needs to know about metaverse: a complete survey on technological singularity, virtual ecosystem, and research agenda. arXiv:211005352
Lesort T, Díaz-Rodríguez N, Goudou J F et al (2018) State representation learning for control: an overview. Neural Netw 108:379–392. https://doi.org/10.1016/j.neunet.2018.07.006. https://www.sciencedirect.com/science/article/pii/S0893608018302053
Louie R, Coenen A, Huang C Z et al (2020) Novice-ai music co-creation via ai-steering tools for deep generative models. In: Proceedings of the 2020 CHI conference on human factors in computing systems, pp 1–13
Lundberg S M, Lee S I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems, p 30
Lundberg SM, Erion GG, Lee SI (2018) Consistent individualized feature attribution for tree ensembles. arXiv:180203888
Lundberg SM, Erion GG, Chen H et al (2019) Explainable ai for trees: from local explanations to global understanding. CoRR arXiv:1905.04610
Lundberg S M, Erion G, Chen H et al (2020) From local explanations to global understanding with explainable ai for trees. Nat Mach Intell 2(1):56–67
Madumal P, Miller T, Sonenberg L et al (2020) Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI conference on artificial intelligence, pp 2493–2500
Miller T (2019) Explanation in artificial intelligence: insights from the social sciences. Artif Intell 267:1–38
Oroojlooy A, Hajinezhad D (2022) A review of cooperative multi-agent deep reinforcement learning. Appl Intell 1–46
Patel K, Fogarty J, Landay J A et al (2008) Investigating statistical machine learning as a tool for software development. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 667–676
Perez-Liebana D, Liu J, Khalifa A et al (2019) General video game ai: a multitrack framework for evaluating agents, games, and content generation algorithms. IEEE Trans Games 11(3):195–214
Powers R, Shoham Y (2004) New criteria and a new algorithm for learning in multi-agent systems. In: Advances in neural information processing systems, p 17
Raffin A, Hill A, Traoré R et al (2019) Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics. In: SPIRL 2019: workshop on structure and priors in reinforcement learning at ICLR 2019
Ramos G, Meek C, Simard P et al (2020) Interactive machine teaching: a human-centered approach to building machine-learned models. Hum–Comput Interact 35(5–6):413–451
Ribeiro M T, Singh S, Guestrin C (2016) “Why should i trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135–1144
Sagi O, Rokach L (2018) Ensemble learning: a survey. Wiley Interdiscip Rev: Data Min Knowl Discov 8(4):e1249
Schapire R E (1999) A brief introduction to boosting. In: Ijcai, citeseer, pp 1401–1406
Sequeira P, Gervasio M (2020) Interestingness elements for explainable reinforcement learning: Understanding agents’ capabilities and limitations. Artif Intell 288:103367
Shi W, Huang G, Song S et al (2020) Self-supervised discovering of interpretable features for reinforcement learning. IEEE Trans Pattern Anal Mach Intell PP:1–1. https://doi.org/10.1109/TPAMI.2020.3037898
Shneiderman B (2020) Human-centered artificial intelligence: reliable, safe & trustworthy. Int J Hum–Comput Interact 36(6):495–504
Silver D, Huang A, Maddison C J et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484–489
Silver D, Hubert T, Schrittwieser J et al (2018) A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362 (6419):1140–1144
Sundararajan M, Najmi A (2020) The many shapley values for model explanation. In: International conference on machine learning, PMLR, pp 9269–9278
Vinyals O, Babuschkin I, Czarnecki W M et al (2019) Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575 (7782):350–354
Vouros GA (2022) Explainable deep reinforcement learning: state of the art and challenges. ACM Comput Surv https://doi.org/10.1145/3527448, just Accepted
Wiegreffe S, Pinter Y (2019) Attention is not not explanation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, pp 11–20. https://doi.org/10.18653/v1/D19-1002. https://aclanthology.org/D19-1002
Yang G, Liu M, Hong W et al (2022) Perfectdou: dominating doudizhu with perfect information distillation. In: NeurIPS
Zha D, Xie J, Ma W et al (2021) Douzero: mastering doudizhu with self-play deep reinforcement learning. In: International conference on machine learning, PMLR, pp 12333–12344
Zhang M, Vikram S, Smith L et al (2019) Solar: deep structured representations for model-based reinforcement learning. In: International conference on machine learning, PMLR, pp 7444–7453
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hu, Z., Liu, H., Xiong, Y. et al. Promoting human-AI interaction makes a better adoption of deep reinforcement learning: a real-world application in game industry. Multimed Tools Appl 83, 6161–6182 (2024). https://doi.org/10.1007/s11042-023-15361-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15361-6