航线交换机制下多船避碰的策略学习与博弈决策

汪洋,刘红超,田池,吴兵,张笛

Multi-ship collision avoidance via route exchange mechanism: strategy learning and game-theoretic decision making

Yang WANG,Hongchao LIU,Chi TIAN,Bing WU,Di ZHANG

图 13 总奖励与平均航线偏移随训练回合的变化

Fig.13 Variation of total reward and average route deviation with training episodes