* add IMPALA algorithm and some common utils

* update README.md

* refactor files structure of impala algorithm; seperate numpy utils from utils

* add hyper parameter scheduler module; add entropy and lr scheduler in impala

* clip reward in atari wrapper instead of learner side; fix codestyle

* add benchmark result of impala; refine code of impala example; add obs_format in atari_wrappers

* Update README.md

* 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

* 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

* 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