Dynamic Multi-Objective Recommendation Via Discrete Soft Actor-Critic

Main Article Content

Dr. Wei Jun Liu
Yiming Chen

Abstract

Modern recommender systems often need to optimize multiple conflicting objectives, such as accuracy, diversity, and novelty. This paper proposes a novel approach, Dynamic Multi-Objective Recommendation via Discrete Soft Actor-Critic (DMOR-DSAC), to address this challenge. DMOR-DSAC employs a reinforcement learning framework with a discrete action space, utilizing the Soft Actor-Critic algorithm to learn a policy that dynamically balances these objectives. Experimental results on benchmark datasets demonstrate the effectiveness of DMOR-DSAC in achieving superior multi-objective performance compared to existing methods.

Downloads

Download data is not yet available.

Article Details

Section

Articles

How to Cite

Dynamic Multi-Objective Recommendation Via Discrete Soft Actor-Critic. (2025). International Research Journal of Library and Information Sciences, 2(05), 1-5. https://doi.org/10.55640/irjlis-v02i05-01

References

Afsar MM, Crump T, Far B (2022) Reinforcement learning based recommender systems: a survey. ACM Comput Surv 55(7):1–38

Alharbe N, Rakrouki MA, Aljohani A (2023) A collaborative filtering recommendation algorithm based on embedding representation. Expert Syst Appl 215:119380

Badia AP, Sprechmann P, Vitvitskyi A, et al. (2020) Never give up: learning directed exploration strategies. arXiv:2002.06038

Cai X, Guo W, Zhao M et al (2023) A knowledge graph-based many-objective model for explainable social recommendation. IEEE Trans Comput Social Syst 10(6):3021–3030

Chen L, Zhu G, Liang W et al (2023) Multi-objective reinforcement learning approach for trip recommendation. Expert Syst Appl 226:120145

Chen H, Dai X, Cai H, et al. (2019a) Large-scale interactive recommendation with tree-structured policy gradient. In: Proceedings of the AAAI conference on artificial intelligence. pp 3312–3320

Chen X, Li S, Li H, et al. (2019b) Generative adversarial user model for reinforcement learning based recommendation system. In: International conference on machine learning. PMLR, pp 1052–1061

Christodoulou P (2019) Soft actor-critic for discrete action settings. arXiv:1910.07207

Cui L, Huang W, Yan Q et al (2018) A novel context-aware recommendation algorithm with two-level svd in social networks. Futur Gener Comput Syst 86:1459–1470

Deng Y, Li Y, Sun F, et al. (2021) Unified conversational recommendation policy learning via graph-based reinforcement learning. In: Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval. pp 1431–1441

Dulac-Arnold G, Evans R, Hasselt HV, et al. (2015) Deep reinforcement learning in large discrete action spaces. Artificial Intelligence. https://api.semanticscholar.org/CorpusID:13512886

Fu M, Agrawal A, Irissappane AA et al (2021) Deep reinforcement learning framework for category-based item recommendation. IEEE Trans Cybern 52(11):12028–12041

Fu M, Huang L, Rao A et al (2022) A deep reinforcement learning recommender system with multiple policies for recommendations. IEEE Trans Industr Inf 19(2):2049–2061

Giannikis S, Frasincar F, Boekestijn D (2024) Reinforcement learning for addressing the cold-user problem in recommender systems. Knowl-Based Syst 294:111752

Haarnoja T, Zhou A, Abbeel P, et al. (2018a) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning. PMLR, pp 1861–1870

Haarnoja T, Zhou A, Hartikainen K, et al. (2018b) Soft actor-critic algorithms and applications. arXiv:1812.05905

Herlocker JL, Konstan JA, Terveen LG et al (2004) Evaluating collaborative filtering recommender systems. ACM Trans Infor Syst 22(1):5–53

Hessel M, Modayil J, Van Hasselt H, et al. (2018) Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence

He K, Zhang X, Ren S, et al. (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. pp 1026–1034

Järvelin K, Kekäläinen J (2002) Cumulated gain-based evaluation of IR techniques. ACM Trans Inform Syst 20(4):422–446

Kasirzadeh A, Evans C (2021) User tampering in reinforcement learning recommender systems. Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society. https://api.semanticscholar.org/CorpusID:237453377

Khurana P, Gupta B, Sharma R et al (2024) Session-aware recommender system using double deep reinforcement learning. J Intell Inform Syst 62(2):403–429

Lei Y, Wang Z, Li W et al (2020) Social attentive deep q-networks for recommender systems. IEEE Trans Knowl Data Eng 34(5):2443–2457

Li D, Li X, Wang J, et al. (2020) Video recommendation with multi-gate mixture of experts soft actor critic. In: Proceedings of the 43rd International ACM SIGIR conference on research and development in information retrieval. pp 1553–1556

Liu D, Yang C (2019) A deep reinforcement learning approach to proactive content pushing and recommendation for mobile users. IEEE Access 7:83120–83136

Liu F, Tang R, Guo H et al (2020) Top-aware reinforcement learning based recommendation. Neurocomputing 417:255–269

Most read articles by the same author(s)