Mikhail ScherbinainTowards Data ScienceTop-K Off-Policy Correction for a REINFORCE Recommender SystemOffKTopPolicy is now available for your usage out of the box with no prerequisites in my Reinforced Recommendation Library!13 min read·Nov 28, 2019----
Mikhail ScherbinainTowards Data ScienceReinforcement Learning (DDPG and TD3) for News RecommendationReinforcement learning as-is is a pretty hard topic. When I started to dig deeper, I realized the need for a good explanation. This…32 min read·Aug 20, 2019--1--1
Mikhail ScherbinainTowards Data ScienceDeep Reinforcement Learning for News Recommendation. Part 1: Architecture.I will be trying to cover this paper, so, if you want more details, consider reading it7 min read·Dec 27, 2018--7--7