* replace tensorboard with summary to support VDL in the future

* unittest

* rename keys for record

* yapf

* state to obs

* yapf & update softlink in offline-q-learning

* remove version 1.3 warnings

* update

* yapf

* add algorithms test

* Update algs_test.py

* Update algs_test.py

add SAC DDPG TD3 tests

* yapf

* fix paddle version bug

* add gym dependence (introduced by MADDPG)

* recall

* add offline q learning

* Update README.md

* update

* yapf