* feature(nyz): add trueskill as league metric, naive elo calculator, fix game_env info bug

* fix(nyz): fix league player mutate bug

* fix(nyz): fix league unittest bug

* feature(nyz): add elo ranking in league metric env

* polish(nyz): modify fixed eval policy and trueskill init

* feature(nyz): add init main player in evaluation and fix stop_value bug

* style(nyz): rename test_league_metric to avoid pyc cache bug

* add modifiled predator_prey env

* add collision_ratio

* add readme and cfg for modified_predator_prey env

* add readme imgs for modified_predator_prey

* check format

* fix format

* add sqil

* conceal all the personal info

* revise according to the comments

* correct_format

* add_comment to hardcodes part

* pass flake8

* add force_reproducibility = True; device, ex_model

* check format

* fix weight bug

* update acer qbert result

* fix flake8 format problem

* update space qbert config

* update as review
Co-authored-by: Nshenziju <simonshen2011@foxmail.com>

* init runable ppo

* init overcooked env

* overcooked ppo in place

* runable ppo with shaped rewards

* modified config

* feature(nyz): modify win rate calculation with draws

* remove redundant code, modified baseline model

* Update __init__.py

* Update config.py

* modify temp_config_file.close() position in config.py to work in windows os

* remove redundant comments and rename files

* fix name bug and use namedlist

* add simple readme and remove redundant comments from copies

* resolve threads

* remove debug comments
Co-authored-by: Nniuyazhe <niuyazhe314@outlook.com>

* feature(nyz): add naive 1v1 two player demo

* feature(nyz): add 1v1 evaluator and 2 rule-based policy for evaluation

* feature(nyz): modify game env and adjust hyper-param

* feature(nyz): add naive league training multi player demo

* feature(nyz): enable force snapshot to support init historical league player; finish league demo basic code

* feature(nyz): modify selfplay demo and add two type game env

* style(nyz): correct format style

* polish(nyz): correct format style and adapt league demo main

* feature(nyz): add league payoff viz and enable payoff update in league demo

* feature(nyz): modify win rate calculation with draws

* test(nyz): fix one vs one league test compatibility bug

* test(nyz): add selfplay and league demo into unittest and algotest

* style(nyz): correct format

* hotfix(nyz): fix ppo continuous comatibility bug

* add endoro env config. add enduro's ppo,dqn,drdqn,rainbow,impala config.

* modified as reviewer mentions

* add qacd network

* fix bugs

* fix bugs

* update acer algorithm

* update ACER code

* update acer config

* fix bug

* update pong acer's config

* edit commit

* update code as mention

* fix the comment table and trust region

* fix format

* fix typing lint

* fix format,flake8

* fix format

* fix whitespace problem

* test(nyz): add acer unittest and algotest

* style(nyz): correct flake8 style
Co-authored-by: Nshenziju <simonshen2011@foxmail.com>
Co-authored-by: NSwain <niuyazhe314@outlook.com>

* add pybullet envs.

* add td3/ddpg/sac/ppo configs for pybullet.

* update td3/ddpg/sac/ppo configs for pybullet.

* update td3 configs; remove td3 model.

* add endoro env config. add enduro's ppo,dqn,drdqn,rainbow,impala config.

* modified as reviewer mentions

* add qacd network

* fix bugs

* update dizoo readme

* add README.md about max reward result

* update dqn config and update README
Co-authored-by: Nshenziju <simonshen2011@foxmail.com>
Co-authored-by: Nsimon shen <simon@simondeMacBook-Air.local>
Co-authored-by: NSwain <niuyazhe314@outlook.com>

on policy ppo (#9)

# Conflicts:
#	ding/policy/common_utils.py
#	ding/policy/ppo.py