arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.00683cs.LGcs.AI
收藏

基于混合深度强化学习方法的垄断决策

Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach

Purdue University(普渡大学);University of Southern California(南加州大学)

Trevor Bonjour, Marina Haliem, Aala Alsalem, Shilpa Thomas, Hongyu Li, Vaneet Aggarwal, Mayank Kejriwal, Bharat Bhargava

摘要:

学习在动态和复杂的环境中适应并做出实时明智的决策是一个具有挑战性的问题。大富翁是一种流行的战略棋盘游戏,要求玩家在游戏过程中做出多个决定。垄断中的决策涉及许多现实世界的因素,如战略,运气和对手的政策建模。在本文中,我们提出了新的表示的状态和动作空间的完整版本的垄断,并定义了一个改进的奖励函数。使用这些,我们证明了我们的深度强化学习代理可以学习垄断对不同的固定政策代理的获胜策略。在大富翁中,玩家可以采取多个行动,即使不是轮到他们掷骰子。这些动作中的一些动作比其他动作发生得更频繁,从而导致对学习代理的性能产生不利影响的偏斜分布。为了解决行动的非均匀分布,我们提出了一种混合方法,将深度强化学习(用于频繁但复杂的决策)与固定策略方法(用于不频繁但简单的决策)相结合。实验结果表明,我们的混合代理比标准的深度强化学习代理在与固定策略代理的比赛中获胜的次数高出30%。

英文摘要:

Learning to adapt and make real-time informed decisions in a dynamic and complex environment is a challenging problem. Monopoly is a popular strategic board game that requires players to make multiple decisions during the game. Decision-making in Monopoly involves many real-world elements such as strategizing, luck, and modeling of opponent's policies. In this paper, we present novel representations for the state and action space for the full version of Monopoly and define an improved reward function. Using these, we show that our deep reinforcement learning agent can learn winning strategies for Monopoly against different fixed-policy agents. In Monopoly, players can take multiple actions even if it is not their turn to roll the dice. Some of these actions occur more frequently than others, resulting in a skewed distribution that adversely affects the performance of the learning agent. To tackle the non-uniform distribution of actions, we propose a hybrid approach that combines deep reinforcement learning (for frequent but complex decisions) with a fixed policy approach (for infrequent but straightforward decisions). Experimental results show that our hybrid agent outperforms a standard deep reinforcement learning agent by 30% in the number of games won against fixed-policy agents.

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。

↑