Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
1.59k
stars
484
forks
source link
Can someone tell me why agents go beyond bounds when testing? #37
Open
glong1997 opened 4 years ago
对，会越界，但是好像有奖励惩罚智能体，只能说环境还是有点问题