arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2003.13741cs.LGcs.AIstat.ML
收藏

连续域上蒙特卡罗树搜索的简化

Parallelization of Monte Carlo Tree Search in Continuous Domains

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Karl Kurzer, Christoph Hörtnagl, J. Marius Zöllner

摘要:

蒙特卡罗树搜索(MCTS)已被证明能够解决围棋、国际象棋和雅达利等领域的挑战性任务。以前的研究已经开发了并行版本的MCTS,利用今天的多处理架构。这些研究集中在离散情况下的MCTS版本。我们的工作建立在现有的并行化策略,并将其扩展到连续域。特别是,叶并行化和根并行化进行了研究,并提出了两个最终的选择策略,需要处理连续状态根并行化。使用具有挑战性的合作多智能体系统的轨迹规划任务,在自动驾驶汽车领域的并行化连续MCTS的评价进行。

英文摘要:

Monte Carlo Tree Search (MCTS) has proven to be capable of solving challenging tasks in domains such as Go, chess and Atari. Previous research has developed parallel versions of MCTS, exploiting today's multiprocessing architectures. These studies focused on versions of MCTS for the discrete case. Our work builds upon existing parallelization strategies and extends them to continuous domains. In particular, leaf parallelization and root parallelization are studied and two final selection strategies that are required to handle continuous states in root parallelization are proposed. The evaluation of the resulting parallelized continuous MCTS is conducted using a challenging cooperative multi-agent system trajectory planning task in the domain of automated vehicles.

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。

↑