Recommender_system_via_deep_RL
Recommender_system_via_deep_RL copied to clipboard
backgom2357
The implemetation of Deep Reinforcement Learning based Recommender System from the paper Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling by Liu et al.
Dear backgom2357: I recently read your code and it was very helpful. At the same time, there are some questions, how to train the class of UserMovieEmbedding to get the...
Hi, I tried running the file train.py. However, when I set load_model = True in recommender.train(MAX_EPISODE_NUM, load_model=False), the file actors_50000.h5 is not found. Could you please tell on how to...
I read your code, find that your code is to do recall, not recommendation。 I didn't see you consider the items order。
Dear author, hello, how did you generate these two files, and did you fully reproduce the paper "Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling"? Thank you!
Hi, It seems that you did not update the state representation network. I can find an optimizer that related to state representation network.
Dear author, I am reproducing this code recently. I have some questions to ask you: 1. Why is the model training "MAX_EPISODE_NUM" set to 8000 ? Is the result better...
Dear author, may I ask why the precision of this model is only about 0.4? Is it possible to improve it? Where did you get the other two files：“actor_50000.h5” “critic_50000.h5”
Where did you obtain the 'user_movie_embedding_case4.h5' file used in your 'recommender.py'? I don't see you saving that file in the 'embedding.ipynb' code. Please explain, thank you
You have divided users into test and train and not their interactions and you have trained to embedding on the whole dataset how can the training step will have all...
Metadata
Owner
Metadata
The implemetation of Deep Reinforcement Learning based Recommender System from the paper Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling by Liu et al.