MADDPG
MADDPG copied to clipboard
starry-sky6688
Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".
self.critic_optim.zero_grad() critic_loss.backward() self.critic_optim.step() self.actor_optim.zero_grad() actor_loss.backward() self.actor_optim.step() 当我把这个顺序调整后，这个会报错：因为inplace操作导致梯度的更新失败。。感激了
Metadata
Owner
Metadata
Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".