* Update README.md

* Create README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.cn.md

* Update README.md

* Update README.md

* Update README.md

* Update README.cn.md

* 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 a3c algorithm, A2C example and rl_utils

* require training in single gpu/cpu

* only check cpu/gpu num in learner

* refine Readme

* update impala benchmark picture; update Readme

* add benchmark result of A2C

* move get_params/set_params in agent_base

* add GA3C example

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* refine Readme

* add benchmark

* add default safe eps in numpy logp calculation

* refine document; make unittest stable

* 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 a3c algorithm, A2C example and rl_utils

* require training in single gpu/cpu

* only check cpu/gpu num in learner

* refine Readme

* update impala benchmark picture; update Readme

* add benchmark result of A2C

* move get_params/set_params in agent_base

* fix shell script cannot run in ubuntu

* refine comment and document

* Update README.md

* Update README.md

* Update remote_decorator.py

* Update README.md

* add an figure for the demonstration about parallelization

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* add a link to IMPALA

* 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 api set_params/get_params in Model; add Interface of Network and LayerFunc to solve circular imports; refine parameter_names api of Model

* remove licence in third party code; remove interface of Network and LayerFunc; move get_parameter_pairs and get_parameter_names api to Network

* refine comment

* refine commment

* Update README.md

* Update train.py

* Update README.md

* Update agent_base.py

* Update train.py

* Update train.py

* Update train.py

* refine remote module, add heartbeat machanism and unittest

* yapf

* yapf

* support get ip address in CentOS, add dependence

* yapf

* add dependence in Dockerfile

* refine message_tag, Compatible with Python2 and python3

* refine unittest and comments

* remove ParlError, use to_pybytes api to compatible with Python 2 and python 3

* Not need to use to_pybytes

* use parl-test docker image for unittest, which has python2 and python3 env

* test different release order of sockets

* test for different closing way fo context and socket

* tmp commit for debug in teamcity

* tmp commit for debug in teamcity

* tmp commit for debug in teamcity

* use zmq.context destroy to close multi-thread socket, refine RemoteError

* set linger=0 for command socket in RemoteObject

* remove close context unittest

* fix codestyle

* fix codestyle

* rename parl.remote to parl.remote_class; will not exit client when having errors in function call; use sepereate server port in unittest to avoiding closing server manually

* rename parl.remote to parl.remote_class; will not exit client when having errors in function call; use sepereate server port in unittest to avoiding closing server manually

* fix typo

* remove unnecessary try/except in reply loop of client

* import RemoteManager to parl; refine comment

* run unittest in python2 and python3

* refine structure of repo

* refine structure of repo

* add --fix-misssing

* fix teamcity

* add --fix-misssing

* update paddle version in python2

* Update model_base.py

* Update README.md

* Update README.md

* first version of network communication

* fix code styple problems

* add a script to get machine's information

* code styple problems#2

* fix unit test problems

* update dockfile to fix the installation issue of cmake

* thread-saftey ensurance & copright

* resolve comments

* fix PPO bug; add more benchmark result

* refine code

* update benchmark of PPO, after fix bug

* refine code

* 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

* remove not used files, add benchmark for DQN and DDPG, add Parameters management Readme

* Update README.md

* Update README.md

* add parl dependence in examples, use np shuffle instead of sklean

* fix codestyle

* refine readme of nips example

* fix bug

* fix code style

* Update README.md

* Update README.md

* Update README.md

* refine document and remove outdated design doc

* Update README.md

* Update README.md

* refine comment

* release version 1.0

* gif of examples

* Update README.md

* update Readme

* Update README.md

* add experimental results

* 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 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 a episode to show the final test reward

* make code more clear

* 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

a more detailed example for DQN model.

* add testing module of NeurIPS2018-AI-for-Prosthetics-Challenge, add dependencies of setup

* add copyright

* add google drive link

* fix depedencie

* refine setup

* Update README.md

* Update README.md

* add diagram/logo

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* 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

code will be released before 31.October (#20)

* 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

add design doc

* simple replay buffer and its test

* add error handling

* add test for deep copy