openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Home Page:https://arxiv.org/pdf/1706.02275.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Nontype flaw in "train.py", line 182

DailinH opened this issue · comments

If one tries to set "--exp-name" by default, an error may occur in train.py(line 182) indicating that there is a TypeError. This may have resulted from the parse_args function's setting "--exp-name"'s default to None. It might be better to set it to "" as in "--load-dir"

i ttried what you said,set default to "", but not work,the error: FileNotFoundError: [Errno 2] No such file or directory: './learning_curves/_rewards.pkl'

the solution to that is to create a learning_curves folder by hand, I guess. mkdir learning_curves will do.

The code in train.py says parser.add_argument("--exp-name", type=str, default=None, help="name of the experiment"). Therefore, when you try to set the argument exp-name, remember to assign a string variable like --exp-name "foo".