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 1807.01081cs.AI
收藏

使用分形和熵解决Atari游戏

Solving Atari Games Using Fractals And Entropy

HCSoft Programación, S.L.(HCSoft编程有限公司)

Sergio Hernandez Cerezo, Guillem Duran Ballester, Spiros Baxevanakis

摘要:

在本文中,我们介绍了一种新的MCTS为基础的方法,是来自热力学定律。该算法被称为分形蒙特卡罗(FMC),它允许我们创建一个在连续和离散环境中采取智能行动的代理,同时提供对代理行为各个方面的控制。结果表明,FMC是几个数量级的效率比类似的技术,如MCTS,在雅达利游戏测试。

英文摘要:

In this paper, we introduce a novel MCTS based approach that is derived from the laws of the thermodynamics. The algorithm coined Fractal Monte Carlo (FMC), allows us to create an agent that takes intelligent actions in both continuous and discrete environments while providing control over every aspect of the agent behavior. Results show that FMC is several orders of magnitude more efficient than similar techniques, such as MCTS, in the Atari games tested.

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。

↑