#?#?Unity?ML?Agents
#?##?Proximal?Policy?Optimization?（PPO）
#?Contains?an?implementation?of?PPO?as?described?[here]（https://arxiv.org/abs/1707.06347）.

from?docopt?import?docopt

import?os
from?ppo.models?import?*
from?ppo.trainer?import?Trainer
from?unityagents?import?UnityEnvironment

_USAGE?=?‘‘‘
Usage:
??ppo?（）?[options]?

Options:
??--help?????????????????????Show?this?message.
??--max-steps=?????????????Maximum?number?of?steps?to?run?environment?[default:?1e6].
??--run-path=??????????The?sub-directory?name?for?model?and?summary?statistics?[default:?ppo].
??--load?????????????????????Whether?to?load?the?model?or?randomly?initialize?[default:?False].
??--train????????????????????Whether?to?train?model?or?only?run?inference?[default:?True].
??--summary-freq=?????????Frequency?at?which?to?save?training?statistics?[default:?10000].
??--save-freq=????????????Frequency?at?which?to?save?model?[default:?50000].
??--gamma=????????????????Reward?discount?rate?[default:?0.99].
??--lambd=????????????????Lambda?parameter?for?GAE?[default:?0.95].
??--time-horizon=?????????How?many?steps?to?collect?per?agent?before?adding?to?buffer?[default:?2048].
??--beta=?????????????????Strength?of?entropy?regularization?[default:?1e-3].
??--num-epoch=????????????Number?of?gradient?descent?steps?per?batch?of?experiences?[default:?5].
??--epsilon=??????????????Acceptable?threshold?around?ratio?of?old?and?new?policy?probabilities?[default:?0.2].
??--buffer-size=??????????How?large?the?experience?buffer?should?be?before?gradient?descent?[default:?2048].
??--learning-rate=?????Model?learning?rate?[default:?3e-4].
??--hidden-units=?????????Number?of?units?in?hidden?layer?[default:?64].
??--batch-size=???????????How?many?experiences?per?gradient?descent?update?step?[default:?64].
??--keep-checkpoints=?????How?many?model?checkpoints?to?keep?[default:?5].
??--worker-id=????????????Number?to?add?to?communication?port?（5005）.?Used?for?asynchronous?agent?scenarios?[default:?0].
‘‘‘

options?=?docopt（_USAGE）
print（options）

#?General?parameters
max_steps?=?float（options[‘--max-steps‘]）
model_path?=?‘./models/{}‘.format（str（options[‘--run-path‘]））
summary_path?=?‘./summaries/{}‘.format（str（options[‘--run-path‘]））
load_model?=?options[‘--load‘]
train_model?=?options[‘--train‘]
summary_freq?=?int（options[‘--summary-freq‘]）
save_freq?=?int（options[‘--save-freq‘]）
env_name?=?options[‘‘]
keep_checkpoints?=?int（options[‘--keep-checkpoints‘]）
worker_id?=?int（options[‘--worker-id‘]）

#?Algorithm-specific?parameters?for?tuning
gamma?=?float（options[‘--gamma‘]）
lambd?=?float（options[‘--lambd‘]）
time_horizon?=?int（options[‘--time-horizon‘]）
beta?=?float（options[‘--beta‘]）
num_epoch?=?int（options[‘--num-epoch‘]）
epsilon?=?float（options[‘--epsilon‘]）
buffer_size?=?int（options[‘--buffer-size‘]）
learning_rate?=?float（options[‘--learning-rate‘]）
hidden_units?=?int（options[‘--hidden-units‘]）
batch_size?=?int（options[‘--batch-size‘]）

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2017-10-18?18:41??ml-agents-master\
?????文件????????1108??2017-10-18?18:41??ml-agents-master\.gitignore
?????文件????????3191??2017-10-18?18:41??ml-agents-master\CODE_OF_CONDUCT.md
?????文件???????11348??2017-10-18?18:41??ml-agents-master\LICENSE
?????文件????????1490??2017-10-18?18:41??ml-agents-master\README.md
?????目錄???????????0??2017-10-18?18:41??ml-agents-master\docs\
?????文件????????5485??2017-10-18?18:41??ml-agents-master\docs\Agents-Editor-Interface.md
?????文件????????3335??2017-10-18?18:41??ml-agents-master\docs\Example-Environments.md
?????文件????????7958??2017-10-18?18:41??ml-agents-master\docs\Getting-Started-with-Balance-Ball.md
?????文件????????3021??2017-10-18?18:41??ml-agents-master\docs\Limitations-&-Common-Issues.md
?????文件???????14901??2017-10-18?18:41??ml-agents-master\docs\Making-a-new-Unity-Environment.md
?????文件????????1719??2017-10-18?18:41??ml-agents-master\docs\Organizing-the-Scene.md
?????文件?????????901??2017-10-18?18:41??ml-agents-master\docs\Readme.md
?????文件????????2881??2017-10-18?18:41??ml-agents-master\docs\Training-on-Amazon-Web-Service.md
?????文件????????3760??2017-10-18?18:41??ml-agents-master\docs\Unity-Agents---Python-API.md
?????文件????????7034??2017-10-18?18:41??ml-agents-master\docs\Unity-Agents-Overview.md
?????文件????????6452??2017-10-18?18:41??ml-agents-master\docs\Using-TensorFlow-Sharp-in-Unity-（Experimental）.md
?????文件????????1217??2017-10-18?18:41??ml-agents-master\docs\best-practices.md
?????文件????????2182??2017-10-18?18:41??ml-agents-master\docs\installation.md
?????目錄???????????0??2017-10-18?18:41??ml-agents-master\images\
?????文件???????88595??2017-10-18?18:41??ml-agents-master\images\academy.png
?????文件???????44453??2017-10-18?18:41??ml-agents-master\images\agent.png
?????文件??????241346??2017-10-18?18:41??ml-agents-master\images\agents_diagram.png
?????文件?????1217166??2017-10-18?18:41??ml-agents-master\images\balance.png
?????文件??????171073??2017-10-18?18:41??ml-agents-master\images\banner.png
?????文件???????73513??2017-10-18?18:41??ml-agents-master\images\brain.png
?????文件??????199636??2017-10-18?18:41??ml-agents-master\images\gridworld.png
?????文件???????76764??2017-10-18?18:41??ml-agents-master\images\internal_brain.png
?????文件???????78014??2017-10-18?18:41??ml-agents-master\images\player_brain.png
?????文件???????46378??2017-10-18?18:41??ml-agents-master\images\scene-hierarchy.png
?????文件??????170182??2017-10-18?18:41??ml-agents-master\images\tennis.png
............此處省略238個(gè)文件信息