Reinforcement learning for Recommendation Systems

Implementation of Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling.

Some of the code were reused from Catalyst demo notebook and higgsfield's RL-Adventure, it helps a lot.

TODO:

• [x] Implement validation
• [x] Change training process (switch to sessions)
• [x] Add Prioritized Experience Replay

Special TODO:

• [x] Add Ornstein–Uhlenbeck noise for better exploration

Movielens (1M) results