Fixed the mapolicy train issue

[FahmidMorshed]

The trained MARL policies were not performing as expected because the parent class (MultiAgentPolicyManager) needed a train function.

• 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

Fixes #967

[codecov-commenter]

Codecov Report

Merging #968 (dcc1493) into master (66b7fc5) will increase coverage by 0.00%.
The diff coverage is 100.00%.

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

@@           Coverage Diff           @@
##           master     #968   +/-   ##
=======================================
  Coverage   90.82%   90.82%           
=======================================
  Files          72       72           
  Lines        5394     5398    +4     
=======================================
+ Hits         4899     4903    +4     
  Misses        495      495           

Flag	Coverage Δ
unittests	90.82% <100.00%> (+<0.01%)	⬆️

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

Files	Coverage Δ
tianshou/policy/multiagent/mapolicy.py	85.41% <100.00%> (+0.63%)	⬆️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more