search

google-research / recsim

A Configurable Recommender Systems Simulation Platform
https://github.com/google-research/recsim
Apache License 2.0
747 stars 129 forks source link

Recommender System step-by-step output #19

Open theolanganay opened 4 years ago

theolanganay commented 4 years ago

Hello,

I am working on a project and we want to use recsim to understand how RL agents on recommender systems work. We created a new environment based on our business case and applied the full-slate-q agent on it, but the only output we have are the reward graphs in the TensorBoard.

Would it be possible to display the step-by-step output for a given user starting state, with the recommandations made by the agent and the choices made by the user to understand better how everything works?

Congrats for the great work and thanks in advance!

Théophile

lubit commented 3 years ago

I have the same doubts...

cwhsu-google commented 3 years ago

Thanks for using RecSim and sorry for the late reply.

Currently we cannot visualize step-by-step output for state transitions and others because it depends on your user/doc representation. For metrics we do have a conventional way to do it and that's why we can use Tensorboard for it. However, you can always dump trajectories by setting episode_log_file and inspect state transitions, recommendations, and choices from there.