* rename namespace

* update torch code

* rename deepes to evokit

* update readme

* Update CMakeLists.txt

* update build.sh

* update code format to meet icode requirement

* update torch code

* update directory structure to support the icode platform

* remove source code generated by protobuf

* move code into the core directory

* add gaussian sampling method with noise table

* add table sampling test and agent param_size test

* add model param_size test

* get param size of paddle demo

* rename gaussian_table_sampling to cached_gaussian_sampling

* add unittest to sampling method and uniform indentation to 2 spaces
Co-authored-by: NTomorrowIsAnOtherDay <2466956298@qq.com>

* remove depedence on predictor.clone()

* remove commented lines

* remove FATAL logging

* remove ESAgent's construnction function based on cxx_config

* mv prototxt

* rename SamplingKey to SamplingInfo

* add asynchronous lsagent

* rename AsyncAgent to AsyncESAgent

* fix comments

* Update async_es_agent.cc

* Sampling Info

* commemt

* commemt

* add es torch effect test

* test the performance using the gtest framework

* update

* delete last blank line of CMakeLists.txt

* optimizer sin demo and use vector for data storage

* optimize sin demo test

* release v1.2.3

* change dep of liftsim a2c

* Add UnitTest for DeepES

* update Dockerfile

* only unittest

* remove the commented lines and empty functions.

* update CMakefile

* add optimizer unittest and torch demo test

* use optimizer_factory and add fail unittest case

* remove duplicate files, and simplify unittest

* teamcity test

* delete test case

* remove comment line

* shield progress display of downloading and unzip libtorch

* remove deepes torch demo test

* delete useless comment

* fix a2c cannot run in paddle 1.6.0

* fix impala compatibility

* yapf

* add optimizer factory

* add file:optimizer_factory

* copyright

* remove dependence on algorithm.h

* fix compatibility issue with the newest paddle

* remove logging lines

* resolve the compatibility issue with the newest paddle

* yapf
Co-authored-by: Nrobot <zenghongsheng@baidu.com>

* add SGD and Adam Optimizer for DeepES

* update deepes readme

* add warning when input different size in the same param update()

* add error return in update(), add optimizer.cc

* separate SGD and Adam, optimizer type in config is not case sensitive

* delete optimizer.cc

* config optimizer in deepes.proto

* more readable

* update maddpg readme, fixed gym version

* add tutorial of deepes, written with numpy, less than 100lines

* modify learning_rate as an arugment of Agent

* fix compatibility issue with the newest paddle

* remove logging lines
Co-authored-by: Nrobot <zenghongsheng@baidu.com>

* mac compatibility

* refine import trick

* liftsim a2c baseline

* update readme

* compatible with different os

* empty

* refine comments

* remove unnecessary assertion; add tensorboard guide

* remove unnecessary assertion

* update parl dependence of A2C

* add deepES & a demo that is compatible with torch

* add copyright & update protoc file path

* add copyright

* rm useless files

* update dependency on libtorch

* add the demonstration gif

* update gif

* Create README.md

* Update README.md

* Update README.md

* Update README.md

* update scripts

* update scripts#2

* update torch_predictor

* update comments for ES

* check dependence on paddle or torch

* update readme

* update readme#2

* users can still use parl.remote when no DL framework was found

* yapf

* add maddpg example

* format with yapf

* fix coding style

* fix coding style

* unittest without import multiagent env

* update maddpg code

* update maddpg readme

* add copyright comments

* update parl.maddpg without import gym

* update NeurlIPS2018.gif to NeurlIPS2019.gif

* update readme and comments

* fix paddle version bug

* add gym dependence (introduced by MADDPG)

* recall

* torch benchmark policy gradient

* refine comments and use native api

* add maddpg example

* format with yapf

* fix coding style

* fix coding style

* unittest without import multiagent env

* update maddpg code

* update maddpg readme

* add copyright comments

* add offline q learning

* Update README.md

* update

* yapf