Keepaway Soccer: A Machine Learning Testbed
Keepaway Soccer: A Machine Learning Testbed
复制标题
Keepaway Soccer：机器学习测试平台
DOI：
10.1007/3-540-45603-1_22
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
R. Sutton
中科院分区：
文献类型：
--
作者：
P. Stone;R. Sutton
RoboCup仿真足球赛对机器学习方法提出了许多挑战，包括大的状态空间、隐藏和不确定的状态、多个代理以及动作效果的长时间和可变延迟。虽然机器学习已经成功地应用于机器人足球任务的一部分，但似乎仍然超出了现代机器学习技术的能力，使一个由11个智能体组成的团队能够成功地学习从传感器到执行器的完整机器人足球任务。由于任务部分的成功应用程序已嵌入到不同的团队中，并且通常解决不同的子任务，因此很难比较。我们提出keepaway soccer作为一个适合直接比较机器人足球不同机器学习方法的领域。它足够复杂，不能简单地解决，但又足够简单，完整的机器学习方法是可行的。在keepaway，一个团队，“守门员”，试图保持控制球尽可能长的时间，尽管努力的“接球手”。守门员要单独学习什么时候持球，什么时候传球给队友，而接球手要学习什么时候冲向持球者，什么时候覆盖可能的传球路线。我们充分说明了域，并总结了一些初步的，成功的学习结果。
RoboCup simulated soccer presents many challenges to machine learning (ML) methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the effects of actions. While there have been many successful ML applications to portions of the robotic soccer task, it appears to be still beyond the capabilities of modern machine learning techniques to enable a team of 11 agents to successfully learn the full robotic soccer task from sensors to actuators. Because the successful applications to portions of the task have been embedded in different teams and have often addressed different sub-tasks, they have been difficult to compare. We put forth keepaway soccer as a domain suitable for directly comparing different machine learning approaches to robotic soccer. It is complex enough that it can’t be solved trivially, yet simple enough that complete machine learning approaches are feasible. In keepaway, one team, “the keepers,” tries to keep control of the ball for as long as possible despite the efforts of “the takers.” The keepers learn individually when to hold the ball and when to pass to a teammate, while the takers learn when to charge the ball-holder and when to cover possible passing lanes. We fully specify the domain and summarize some initial, successful learning results.