Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

26 行
835 B

import argparse
from typing import Optional, List
from mlagents.trainers.learn import RunOptions, run_cli, load_config
def parse_command_line(argv: Optional[List[str]] = None) -> argparse.Namespace:
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument("experiment_config_path")
return parser.parse_args(argv)
def main():
"""
Provides an alternative CLI interface to mlagents-learn, 'mlagents-run-experiment'.
Accepts a JSON/YAML formatted mlagents.trainers.learn.RunOptions object, and executes
the run loop as defined in mlagents.trainers.learn.run_cli.
"""
args = parse_command_line()
expt_config = load_config(args.experiment_config_path)
run_cli(RunOptions(**expt_config))
if __name__ == "__main__":
main()