JohannesAck/MATD3implementation

Code for the RL method MATD3 described in the paper "Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics"

语言：Python · GitHub 星标：96 · Fork：14

话题：maddpg · multiagent-reinforcement-learning · reinforcement-learning · rl · td3

在 GitHub 上查看原仓库