feature(gry): add MDQN algorithm

[ruoyuGao]

Description

Implementation of Munchausen Reinforcement Learning

Experiment result (Asterix)

Reward

Action gap

Check List

• merge the latest version source branch/repo, and resolve all the conflicts
• pass style check
• pass all the tests

[codecov]

Codecov Report

Merging #590 (1f72e24) into main (55898a3) will increase coverage by 0.22%.
The diff coverage is 95.23%.

@@            Coverage Diff             @@
##             main     #590      +/-   ##
==========================================
+ Coverage   83.39%   83.61%   +0.22%     
==========================================
  Files         564      565       +1     
  Lines       45781    46407     +626     
==========================================
+ Hits        38178    38804     +626     
  Misses       7603     7603              

Flag	Coverage Δ
unittests	83.61% <95.23%> (+0.22%)	⬆️

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

Impacted Files	Coverage Δ
ding/policy/mdqn.py	90.00% <90.00%> (ø)
ding/entry/serial_entry.py	96.92% <100.00%> (ø)
ding/policy/__init__.py	100.00% <100.00%> (ø)
ding/policy/command_mode_policy_instance.py	93.49% <100.00%> (+0.10%)	⬆️
ding/rl_utils/__init__.py	100.00% <100.00%> (ø)
ding/rl_utils/td.py	93.34% <100.00%> (+0.37%)	⬆️
ding/rl_utils/tests/test_td.py	100.00% <100.00%> (ø)
ding/framework/event_loop.py	90.16% <0.00%> (-3.28%)	⬇️
ding/interaction/tests/test_utils/stream.py	75.00% <0.00%> (-2.78%)	⬇️
ding/worker/collector/comm/flask_fs_collector.py	89.38% <0.00%> (-0.89%)	⬇️
... and 213 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.