feature(wzl): decision transformer code adaptation on BipedalWalker and Hopper

[zerlinwang]

Description

• Repaired some bugs on decision transformer for continous env (e.g., BipedalWalker)
• Corrected some inproper param names

Related Issue

#291

TODO

• For d4rl Hopper adaptation and test

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 #327 (c868a8d) into main (0a39b43) will decrease coverage by 0.37%.
The diff coverage is 38.67%.

❗ Current head c868a8d differs from pull request most recent head bcf5572. Consider uploading reports for the commit bcf5572 to get more accurate results

@@            Coverage Diff             @@
##             main     #327      +/-   ##
==========================================
- Coverage   86.34%   85.97%   -0.38%     
==========================================
  Files         517      521       +4     
  Lines       40046    40896     +850     
==========================================
+ Hits        34578    35160     +582     
- Misses       5468     5736     +268     

Flag	Coverage Δ
unittests	85.97% <38.67%> (-0.38%)	⬇️

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

Impacted Files	Coverage Δ
ding/entry/serial_entry_decision_transformer.py	0.00% <0.00%> (ø)
ding/rl_utils/__init__.py	100.00% <ø> (ø)
ding/policy/decision_transformer.py	18.07% <18.07%> (ø)
ding/utils/data/dataset.py	54.97% <24.07%> (-13.46%)	⬇️
ding/rl_utils/td.py	91.74% <25.00%> (-1.25%)	⬇️
ding/model/template/decision_transformer.py	96.55% <96.55%> (ø)
ding/model/template/__init__.py	100.00% <100.00%> (ø)
.../model/template/tests/test_decision_transformer.py	100.00% <100.00%> (ø)
ding/policy/command_mode_policy_instance.py	94.84% <100.00%> (+0.10%)	⬆️
ding/framework/message_queue/tests/test_redis.py	33.33% <0.00%> (-66.67%)	⬇️
... and 192 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 0dd424c...bcf5572. Read the comment docs.