Deep Reinforcement Learninig

Created: 2022-03-24 16:08

This paper is about a news recommendation system, DRN.

This paper proposes an approach to solve Cold-start problem with RL and bi-clustering.

Contextual-bandit approach has shown superior recommendation performance in real-world applications.

References

1. https://arxiv.org/pdf/1707.07435.pdf
2. https://dl.acm.org/doi/pdf/10.1145/3178876.3185994
3. https://arxiv.org/pdf/1801.05532.pdf
4. https://arxiv.org/pdf/1003.0146.pdf

Tags

#drl