Not sure how to use this package

[Shentao-YANG]

Dear author,

Thanks for providing this package.

After reading the readme I am still fuzzy about how to train and evaluate the algorithm. Could you please provide (a set of) example commands for the entire process?

Given that some of the users may not be familiar with the hydra package, would you mind providing the example for the following non-default setting:

1. env.name=halfcheetah-medium-expert-v2
2. the policy improvement operator is ``Easy BCQ"
3. seed=2022

Thanks!