search

shariqiqbal2810 / MAAC

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019
MIT License
676 stars 173 forks source link

How to run your code in other scenarios, i.e., cooperative navigation #9

Closed soada closed 5 years ago

soada commented 5 years ago

Hi, thanks for your great job! I met a problem when I run your code in other scenarios, i.e., simple_spread. The command I used is " python main.py simple_spread dataxx --use_gpu". Is it caused by the version of gym. I have tested both gym 0.9.4 and 0.12.5, but the following problem still exists. Could you please give me some advice on the problem? Thanks very much! image image

shariqiqbal2810 commented 5 years ago

Hi,

This looks like it was caused by the gym version not matching the one I specify in the README.

soada commented 5 years ago

Thanks for your comments! I have found that the gym version 0.9.4 is not matched with the baseline version. image When installing the baselines, the following problem occurs: image Could you please give me some advice? Thanks!

shariqiqbal2810 commented 5 years ago

It looks like the version of baselines you are using (0.1.5) is wrong. Please check the README. There is a specific commit that I used, so you need to clone the repo, check out that commit, and install using pip install -e . from the base directory.

soada commented 5 years ago

Thank you very much! I have solved the problem!