Implement CQLPolicy and offline_cql example

[thkkk]

• I have marked all applicable categories:
  • exception-raising fix
  • algorithm implementation fix
  • documentation modification
  • new feature
• I have reformatted the code using make format (required)
• I have checked the code using make commit-checks (required)
• If applicable, I have mentioned the relevant/related issue(s)
• If applicable, I have listed every items in this Pull Request below

This PR implements CQLPolicy, which could be used to train an offline agent in the environment of continuous action space. An experimental result 'halfcheetah-medium-v1' is provided, which is a d4rl environment (for Offline Reinforcement Learning).

Example usage is in the examples/offline/offline_bcq.py. Document modification and unit test for CQLPolicy are also completed.

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 94.42%. Comparing base (a59d96d) to head (e855038).
Report is 548 commits behind head on master.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #506      +/-   ##
==========================================
+ Coverage   94.18%   94.42%   +0.24%     
==========================================
  Files          62       63       +1     
  Lines        4127     4252     +125     
==========================================
+ Hits         3887     4015     +128     
+ Misses        240      237       -3     

Flag	Coverage Δ
unittests	94.42% <100.00%> (+0.24%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.