polish(gry): polish reward model and td error

[ruoyuGao]

Description

• add the config table for each reward model
• remove unuse parameter
• add comment for td error

Related Issue

TODO

Check List

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

[PaParaZz1]

why linear here, there maybe some more complicated networks

[ruoyuGao]

because our remodel network is linear, should we change this comment?

[codecov]

Codecov Report

Merging #624 (d7d16ac) into main (405191d) will decrease coverage by 0.08%.
The diff coverage is 91.66%.

❗ Current head d7d16ac differs from pull request most recent head 2d741e8. Consider uploading reports for the commit 2d741e8 to get more accurate results

@@            Coverage Diff             @@
##             main     #624      +/-   ##
==========================================
- Coverage   83.03%   82.96%   -0.08%     
==========================================
  Files         570      570              
  Lines       47037    46955      -82     
==========================================
- Hits        39056    38954     -102     
- Misses       7981     8001      +20     

Flag	Coverage Δ
unittests	82.96% <91.66%> (-0.08%)	⬇️

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

Impacted Files	Coverage Δ
ding/framework/task.py	93.55% <ø> (ø)
ding/policy/a2c.py	91.20% <ø> (ø)
ding/policy/acer.py	93.95% <ø> (ø)
ding/policy/atoc.py	90.90% <ø> (ø)
ding/policy/collaq.py	86.88% <ø> (ø)
ding/policy/coma.py	91.96% <ø> (ø)
ding/policy/d4pg.py	96.38% <ø> (ø)
ding/policy/ddpg.py	88.00% <ø> (ø)
ding/policy/decision_transformer.py	18.07% <ø> (ø)
ding/policy/il.py	27.77% <ø> (ø)
... and 52 more

... and 63 files with indirect coverage changes

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