search

openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
https://arxiv.org/pdf/1706.02275.pdf
MIT License
1.66k stars 494 forks source link

There is no provision to run ddpg. #33

Open frenzytejask98 opened 5 years ago

frenzytejask98 commented 5 years ago

I typed the policy as 'lol' and it still gives the same result. The readme says that we can run the experiments for ddpg as well as maddpg which is definitely not working.

SHITIANYU-hue commented 4 years ago

I also find the same problem

CHH3213 commented 4 years ago

I typed the policy as 'lol' and it still gives the same result. The readme says that we can run the experiments for ddpg as well as maddpg which is definitely not working.

Hi,do you know how we can run the experiments for ddpg now?

medhijk commented 2 years ago

Has anyone found a solution to this? I am facing the same problem. It's giving me the same result for any policy name argument.