CORL:一个连续状态偏移动力学强化学习CORL: A Continuous-state Offset-dynamics Reinforcement Learner |
|
课程网址: | http://videolectures.net/uai08_brunskill_corl/ |
主讲教师: | Emma Brunskill |
开课单位: | 卡内基梅隆大学 |
开课时间: | 2008-07-30 |
课程语种: | 英语 |
中文简介: | 连续状态空间和随机开关动力学描述了许多丰富的现实世界领域,例如机器人在不同地形上的导航。我们描述了一种用于这些领域学习的强化学习算法,并证明了在某些环境下,该算法可能是近似正确的,其样本复杂度与状态空间维数呈多项式关系。不幸的是,对于这样的问题,通常不存在最优的规划技术;相反,我们使用拟合值迭代来解决所学的MDP,并且在我们的边界中包含由于近似规划而产生的错误。最后,我们报告了一个使用机器人汽车在不同地形上行驶的实验,证明这些动力学表示能够充分捕捉真实世界的动力学,并且我们的算法可以有效地解决这些问题。 |
课程简介: | Continuous state spaces and stochastic, switching dynamics characterize a number of rich, real world domains, such as robot navigation across varying terrain. We describe a reinforcement learning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in our bounds. Finally, we report an experiment using a robotic car driving over varying terrain to demonstrate that these dynamics representations adequately capture real-world dynamics and that our algorithm can be used to efficiently solve such problems. |
关 键 词: | 学习者; 计算机科学; 人工智能 |
课程来源: | 视频讲座网 |
最后编审: | 2020-06-12:邬启凡(课程编辑志愿者) |
阅读次数: | 48 |