Posts tagged “{{ tag }}”

Offline Evaluation for Reinforcement Learning-based Recommendation - A Critical Issue and Some Alternatives

We discussed offline evaluation for RL-based recommender systems and noted that the most common evaluation protocol, i.e., next-item prediction, is unsuited to such approaches.

Generative Slate Recommendation with Reinforcement Learning

Learning to recommend slates with RL is hard, because of the combinatorial action-space. Instead of making assumptions on user behavior, we tried taking actions in the latent space of a VAE, which then decodes slates.

Articles Tagged: "Reinforcement learning"

Offline Evaluation for Reinforcement Learning-based Recommendation - A Critical Issue and Some Alternatives

Generative Slate Recommendation with Reinforcement Learning