Multiagent cooperation and competition with deep reinforcement learning
论文复现:tensorflow_2player_pong论文详述Multiagentcooperationandcompetitionwithdeepreinforcementlearningponggame-twoagents基础模型:ponggame,twoagents算法结构:dqnreward:scoring:(-1,1)conceding(-1)未击中球得-1,击中球得分between(