* 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

* add TD3

* update

* yapf.....

* Update train.py

* 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 pytorch a2c

* add set/get_weights test & copyright

* yapf....

* Update model_base_test_torch.py

* update

* Delete banma.py

* Update model_base_test_torch.py

* update

* Update model.py

* update torch tests

* Update model_base_test_torch.py

* add Double & Dueling DQN

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

* update

* Update train.py

* torch test env

* Update build.sh

* update torch unit test

* git commit -m torchdqn

* yapf

* fix bugs

* fix bugs

* fix bugs

* yapf

* remove fstring format

* torch_test yapf

* yapf

* Add torch in unittest.requirements

* update torch_unittest

* Torch and FLUID conflict problem in __init__.py

* Unittest fail for torch when both torch and fluid exists.

* cluster_test fail in the unittest, add timeout seconds.

* Torch backend for PARL

* add sleep time for unit test send_job_test.py

* Unit test for send_job_test.py

* use multiple try for unit test

* Fix compatibility for python2.7.

* fix send_job_test.py bugs

* check file exist before send_job_test.py

* Modify send_job_test.py

* Limit impala to single GPU training

* refine comment of scheduler

* refine comment

* clear the directory for the function

* add the unit test

* unit test bug

* yapf

* Add `files` argument when creating a client.

* Add `distributed_files` to parl.connect

* yapf

* Add try exception for `cls=cloudpickle.loads()`

* yapf

* unittest cluster_status_test.py `address is used`.

* Solve port address duplicate problem.

* combine two try except

* check monitor for xparl status

* yapf

* fix bugs

* fix bugs

* More sleep in cluster_test.py.

* yapf

* add debug mode

* add debug model

* Fix reset_job_test.py timeout problem.

* remove time decorator

* Add timeout_decorator

* fix the thread-safe problem of  parl.client

* yapf

* Add total CPU nums to monitor

* fix unittest keyerro

* yapf

* test_max_memory error, add more sleep time

* Add more sleep time in job._reply_client_heartbeat

* Try sleep 6 times to check actor number.

* update layer wrappers to align latest fluid

* update version

* fix minor probmels in the docs

* typo

* remove pip source

* fix monitor

* add performance of A2C

* Update README.md

* modify logger for GPU detection

* add favicon

* Sleep longer for unittest.

* fix unittest bugs

* increase sleep seconds after job_memory error

* fix css max-width bug

* check if monitor_port is used

* change master log dir to .parl_data/master/port

* Add docs/parallel_training/features.rst

* rename feature.rst to overview.rst

* Add xparl status & @remote_class(max_memory)

* fix yapf error

* use new remote/tests

* reply job_memory_info to client heartbeat

* add cluster_status_test.py

* update overview.rst

* Update docs

* upgrade unit test to reduce test time

* minor change

* fix the bug in unit tests

* fix the bug in build.sh

* Update build.sh

* Update test.sh

* fix a potential bug that will hung the test

* then

* solve the problem in documentation

* make remote client support multiprocessing

* refine unittest

* refine unittest

* refine comment

* Add parl monitor.

* Add clustermonitor.py

* Fix thread safety bug.

* Fix js bugs.

* Fix End of Files.

* fix cluster_test bug

* yapf error

* fix bugs in tests/job_center_test.py

* fix bugs in tests/job_center_test.py

* add test_cluster_monitor.py

* add worker.exit in test_cluster_monitor.py

* ES example

* refine settings

* fix yapf

* refine documentation; remove csv logger

* fix bug

* merge learner.py and train.py; add version requirements of gym and atari_py

* unify actor num

* fix bug of ParamAttr

* refine imports of unittest

* fix a number of bug

* update comments

* paddle license

* revert the change on client_not_init_test.py

* fix timeout bug & unnitest

* add unit test for potential bugs

* yapf

* unit test

* logger

* logger#2

* fix job's bug that will cause dead-lock

* fix bug

* add missing files

* solve hanging

* fix comments; exit job completely

* hanging problem

* hanging problem#2

* hanging_program#3

* CMAKE

* remove unused variables

* fix bug: removing the job from the cluster twice; add test scripts

* fix attribute error

* fix comment

* rename

* fix the bug in unit test

* remove queue

* fix the vital issue on compatibility

* resolve the warning log

* yapf

* yapf

* first pr

* start a worker when the master is started.

* First PR & Fix logger bugs.

* update docs for a2c, impala and ga3c

* update doc

* yapf modification

* update logger

* yapf correct

* yapf

* setup.py

* old setup.py

* worker 86

* release version 1.1.1

* add version requirement of tensorboard

* new feature: save params

* add unittest for save()/retore()

* add an example demonstrating the usage

* rename the variable

* yapf

* fix comment

* fix the compatibility issue

* fix the comment issue

* support paddle 1.5.1 and replace PE with compiler

* yapf&copyright

* yapf

* fix the teamcity problem

* fix the teamcity problem

* fix comment

* only support paddle 1.5.1

* Cmake

* fix comment

* add documentaion for basic classes

* change the order of three basic classes

* fix commemt & yapf

* comment #2

* yapf#3

* fix commemt@zhs

* minor change

* modify comment

* Update algorithm.py

* Update agent.py

* Update algorithm.py

* fix issue#101

* yapf

* fix some problems of tensorboard

* yapf