一种用于单人麻将的新型奖励塑形函数
A Novel Reward Shaping Function for Single-Player Mahjong
AI总结:
针对麻将状态空间大且奖励稀疏的问题,提出一种新型奖励塑形函数,为协同牌型赋予更高价值,结合前向搜索,在1对1模拟对战中平均每千局多赢1.37美元。
摘要:
麻将是一种状态空间极大且难以处理、奖励极其稀疏的复杂游戏,这给开发麻将智能体带来了挑战。为了克服这一问题,采用了“上听”函数作为奖励塑形函数,并将其与前向搜索算法相结合,创建了一个能够在单人麻将中完成胡牌的智能体(在10,000局游戏中平均需35步操作)。为了提升性能,我们提出了一种新颖的奖励塑形函数,该函数为协同性强的麻将牌型赋予更高的相对价值。在模拟的1对1对战中,使用新奖励函数的智能体表现优于默认的“上听”函数,在1,000局游戏中平均赢得1.37美元。
英文摘要:
Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an agent capable of completing a winning hand in Single-player Mahjong (an average of 35 actions over 10,000 games). To increase performance, we propose a novel bonus reward shaping function, which assigns higher relative values to synergistic Mahjong hands. In a simulated 1-v-1 battle, usage of the new reward function outperformed the default ShangTing function, winning an average of $1.37 over 1000 games.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。