* add PPO example

* Update Readme

* Update Readme

* fix codestyle

* Update Readme

* refine action mapping

* add more unitest case

* remove unnecessary params initialize, add more comments, add benchmark result

* rename

* remove PARL dependence in readme of examples

* Provide synchronizable create_parameter in PARL

* use AttrHold to make LayerFunc support more than two parameters

* refine code

* refine code

* fix #25 

* 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

* add setup.py for installation

* rename agent.py to make it consistent with other framework base

* namespace bug

* sync paras in program, fix deepcopy bug, python3 compatibility

* refactor code, add plutil directory, clean import order

* remove old comment

* refine comment

* fix codestyle

* cache sync program, add gputils module, refine model_base unittest

* fix codestyle

* refine sync params cache

* add fetch_value module

* add logger module

* refine comment

* add license

* refine set_level api

* refine unittest

* fix codestyle with yapf

* add termcolor dependency

* redesign basic class in PARL

* code style fixed

* update yaml's version

* update yaml's version & update code to fix style problem

* add debug message for  function

* delete test code

* rename function: has_fun -> has_func

* fix wrapper of dynamic_lstm cannot support h_0 and c_0 initialization, fix bug of wrapper of dynamic_gru

* use sampling_id of fluid to sampling ids

* remove test simple games unittest, avoid timeout

* change pip source

added test_simple_games

* prelimary implementations of ComputationTask, Algorithm and Model classes

* remove "model_func" from the args of an algorithm

* a clean clone() function for Algorithm and Model

* add use_next_value as a input to learn()

* further re-structure

* added Feedforward and RLAlgorithm classes

* maxid -> argmax

* discrete_distribution -> category_distribution

* category -> categorical

* revisions

* simple replay buffer and its test

* add error handling

* add test for deep copy