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
1.59k stars 484 forks source link

what's benchmark used for? #35

Open KK666-AI opened 4 years ago

KK666-AI commented 4 years ago

FYI

x45w commented 1 year ago

What should I do if my benchmark report is wrong?

2023-05-18 13:40:39.690276: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA Traceback (most recent call last): File "train.py", line 196, in train(arglist) File "train.py", line 84, in train env = make_env(arglist.scenario, arglist, arglist.benchmark) File "train.py", line 61, in make_env env = MultiAgentEnv(world, scenario.reset_world, scenario.reward, scenario.observation, scenario.benchmark_data) AttributeError: 'Scenario' object has no attribute 'benchmark_data'