* feature(zym): add offlineRL algo Discrete CQL.

* feature(zym): add offlineRL algo Discrete CQL; add hdf5 dataset for offlineRL.

* feature(zym): add pybullet env info; add entropy type in sac.

* feature(zym): add cql; add serial entry for offlineRL.

* feature/polish(zym): add generation entry in mujoco env for offlineRL; polish cql/serial entry for offlineRL.

* feature(lj): add d4rl env for offlineRL.

* polish(zym): polish cql.

* feature/polish(zym): add dataset registry; polish offlineRL pipeline.

* fix(zym): fix bug in d4rl/mujoco config; fix bug in dataset for offlineRL.

* style(zym): add pybulletgym and d4rl requirements in setup.

* fix/polish(zym): support str in NaiveRLDataset; polish cql.

* polish(zym): polish command policy.

* feature(zym): add cql in pendulum env; add unittest/algotest for cql.

* fix(zym): fix cql bug in unittest/algotest for cql.