RL4RS
RL4RS is a real-world deep reinforcement learning recommender system benchmark for practitioners and researchers.
Github Page: https://github.com/fuxiAIlab/RL4RS
Dataset Download(data only): https://zenodo.org/record/6622390#.YqBBpRNBxQK
Dataset Download(for reproduction): https://drive.google.com/file/d/1YbPtPyYrMvMGOuqD4oHvK0epDtEhEb9v/view?usp=sharing
Paper: https://arxiv.org/pdf/2110.11073.pdf
Kaggle Competition (old version): https://www.kaggle.com/c/bigdata2021-rl-recsys/overview
Resource Page: https://fuxi-up-research.gitbook.io/fuxi-up-challenges/
key features
two real-world datasets: Besides the artificial datasets or semi-simulated datasets, RL4RS collects the raw logged data from one of the most popular games released by NetEase Game, which is naturally a sequential decision-making problem.
data understanding tool: RL4RS provides a data understanding tool for testing the proper use of RL on recommendation system datasets.
advanced dataset setting: RL4RS provides the separated data before and after reinforcement learning deployment for each dataset, which can simulate the difficulties to train a good RL policy from the dataset collected by SL-based algorithm.
model-free RL: RL4RS supports state-of-the-art RL libraries, such as RLlib and Tianshou. We provide the example codes of state-of-the-art model-free algorithms (A2C, PPO, etc.) implemented by RLlib library on both discrete and continue (combining policy gradients with a K-NN search) RL4RS environment.
offline RL: RL4RS implements offline RL algorithms including BC, BCQ and CQL through d3rlpy library. RL4RS is also the first to report the effectiveness of offline RL algorithms (BCQ and CQL) in RL-based RS domain.
RL-based RS baselines: RL4RS implements some algorithms proposed in the RL-based RS domain, including Exact-k and Adversarial User Model.
offline RL evaluation: In addition to the reward indicator and traditional RL evaluation setting (train and test on the same environment), RL4RS try to provide a complete evaluation framework by placing more emphasis on counterfactual policy evaluation.
low coupling structure: RL4RS specifies a fixed data format to reduce code coupling. And the data-related logics are unified into data preprocessing scripts or user-defined state classes.
file-based RL environment: RL4RS implements a file-based gym environment, which enables random sampling and sequential access to datasets exceeding memory size. It is easy to extend it to distributed file systems.
http-based vector Env: RL4RS naturally supports Vector Env, that is, the environment processes batch data at one time. We further encapsulate the env through the HTTP interface, so that it can be deployed on multiple servers to accelerate the generation of samples.
experimental features (welcome contributions!)
A new dataset for bundle recommendation with variable discounts, flexible recommendation trigger, and modifiable item content is in prepare.
Take raw feature rather than hidden layer embedding as observation input for offline RL
Model-based RL Algorithms
Reward-oriented simulation environment construction
reproduce more algorithms (RL models, safe exploration techniques, etc.) proposed in RL-based RS domain
Support Parametric-Action DQN, in which we input concatenated state-action pairs and output the Q-value for each pair.
installation
RL4RS supports Linux, at least 64 GB Mem !!
Github (recommended)
Dataset Download (Google Driver)
Dataset Download: https://drive.google.com/file/d/1YbPtPyYrMvMGOuqD4oHvK0epDtEhEb9v/view?usp=sharing
two ways to use this resource
Reinforcement Learning Only
start from scratch (batch-rl, environment simulation, etc.)
reported baselines
supported algorithms (from RLlib and d3rlpy)
examples
See script/ and reproductions/.
RLlib examples: https://docs.ray.io/en/latest/rllib-examples.html
d3rlpy examples: https://d3rlpy.readthedocs.io/en/v1.0.0/
reproductions
See reproductions/.
contributions
Any kind of contribution to RL4RS would be highly appreciated! Please contact us by email.
community
citation
Last updated