* fix self.alg

* torch agent initialization

* remove definition of self.alg in PPO

* replace self.algorithm with self.alg

* remove unnecessary definition of self.alg

* fix cn readme

* unittest

* yapf

* add tutorials

* yapf

* yapf

* copyright

* yapf

* update tutorial lesson5

* delete drawing code

* yapf

* remove action_mapping

* update dqn and add README

* update

* update

* yapf

* add toturials homework

* update tutorials

* add tutorials

* yapf

* yapf

* copyright

* yapf

* update tutorial lesson5

* delete drawing code

* yapf

* remove action_mapping

* update dqn and add README

* update

* update

* yapf

* upgrade DQN's lr interface compatibility

* yapf

* update example DQN

* replace tensorboard with summary to support VDL in the future

* unittest

* rename keys for record

* yapf

* update ddpg

* Update train.py

* use cartpole-v0 in dqn

* Update README.md

* 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

* remove version 1.3 warnings

* update

* yapf

* add algorithms test

* Update algs_test.py

* Update algs_test.py

add SAC DDPG TD3 tests

* yapf

* release v1.2.3

* change dep of liftsim a2c

* fix a2c cannot run in paddle 1.6.0

* fix impala compatibility

* yapf

* 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

* 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

* 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

* fix paddle version bug

* add gym dependence (introduced by MADDPG)

* recall

* 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

* add sac

* Training pipeline of NeurIPS2019-Learn-to-Move-Challenge

* fix grammar mistakes

* release 1.2.1

* copyright

* fix bug

* refine README

* refine README

* fix typo

* Update README.md

* Update README.md

* Update reward calculation in QuickStart

* update

* yapf

* Update train.py

remove create_actors thread in train.py

* Update GA3C train.py

* add TD3

* update

* yapf.....

* Update train.py

* update dqn readme

* update merge.png

* make job run task in a separate process

* fix typo

* add more debug info in xparl client

* refine control flow of different processes in xparl job

* refine control flow of different processes in xparl job

* remove tsinghua source

* remove tsinghua source

* remove unnecessary logic

* fix typo

* refine comments and some logic

* fix bug, `decay=0` means totally synchronize weights of source model to target model

* add save_param in docs and quickstart

* Update train.py

* final submit models of NeurIPS2019 challenge

* update readme

* fix yapf

* refine comment

* add Double & Dueling DQN

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

* update

* Update train.py

* add dygraph pg

* update acc. comments

* update comments

* Limit impala to single GPU training

* refine comment of scheduler

* refine comment