Poor RL Documentation: Outdated Configs and Missing Data。 Where is the data of RL？

[duoyw]

I noticed that in the RL example (https://qlib.readthedocs.io/en/latest/component/rl/quickstart.html#), train yml needs to be configured, but the sample yml provided in the documentation cannot run at all, as it contains a large number of outdated parameters. And some data is missing, such as: order_dir:./data/training_order_split
data_dir: ./data/pickle_dataframe/backtest

[aleph23]

Yes. And docs are rather lacking too. This seems to be very much a DIY project. Reverse Engineer while working on your Quant.