* 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

* add simple dqn

* Update README.md

* Update train.py

* update

* update image in README

* update readme

* simplify

* yapf

* Update README.md

* Update README.md

* Update README.md

* Update train.py

* yapf

* add Double & Dueling DQN

* yapf......................

* update

* Update train.py

* intra-version: move parl.framework into parl.core.fluid

* add folder: parl.core

* remove former test folders

* yapf

* yapf0.24

* Update README.md

* Update train.py

* Update README.md

* Update agent_base.py

* Update train.py

* Update train.py

* Update train.py

* add more dqn benchmark result; unify train scripts

* resize benchmark picture

* resize benchmark picture, refine comments of args

* change dependence, mujoco only support python3 now

* NeurIPS2018-AI-for-Prosthetics-Challenge training code

* remove model_zoo, provide download link

* remove model_zoo, provide download link

* add restore_from_one_head api, refine README, fix logger bug

* fix test bug

* fix rpm bug, refine ddpg train script

* fix rpm bug, refine Readme

* add DDPG example, fix some tiny bug

* add license

* unify code structure

* unify code structure

* refine gputils, fix seed in QuickStart

* use white noise in DDPG

* fix codestyle

* add QuickStart example, refine DQN example

* add examples link

* refine the naming, and add quick start training result

* add DQN example, add Agent unittest

* refine readme

* refine  code

* simplify code