/DeepRLRecommenderSystem

Primary LanguageJupyter Notebook

Deep RL-based Recommender System

Paper and code - Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling

https://arxiv.org/pdf/1810.12027.pdf

Code available at: https://github.com/backgom2357/Recommender_system_via_deep_RL

To check our training results, use the actor model and the critic model after 5000 epochs of training.

Dataset used available on Kaggle

Precision first 50 epochs

training precision first 50

Precision first 100 epochs

training precision first 100

Precision first 1500 epochs

training precision first 1500

Precision first 5000 epochs

training precision first 5000

For the embedding model, consult visualisations here

Related articles:

  • [28] X. Zhao, L. Zhang, Z. Ding, D. Yin, Y. Zhao, and J. Tang, “Deep reinforcement learning for list-wise recommendations,” CoRR, vol. abs/1801.00209, 2018. Available here

  • [32] Y. Hu, Q. Da, A. Zeng, Y. Yu, and Y. Xu, “Reinforcement learning to rank in e-commerce search engine: Formalization, analysis, and application,” CoRR, vol. abs/1803.00710, 2018 Available here

  • [19] G. Zheng, F. Zhang, Z. Zheng, Y. Xiang, N. J. Yuan, X. Xie, and Z. Li, “DRN: A deep reinforcement learning framework for news recommendation,” in WWW 2018, Lyon, France, April 23-27, 2018, 2018, pp. 167–176. Available here

  • [29] X. Zhao, L. Zhang, Z. Ding, L. Xia, J. Tang, and D. Yin, “Recommendations with negative feedback via pairwise deep reinforcement learning,” CoRR, vol. abs/1802.06501, 2018. Available here

Team discussion - summary of all the above articles

Check our presentation here