图 书 馆
行动与知觉的质性学习者The Qualitative Learner of Action and Perception, QLAP |
|
| 课程网址: | http://videolectures.net/aaai2010_mugan_qlap/ |
| 主讲教师: | Jonathan Mugan; Benjamin Kuipers |
| 开课单位: | 奥斯丁德克萨斯大学 |
| 开课时间: | 2010-09-01 |
| 课程语种: | 英语 |
| 中文简介: |  该视频介绍了行动和感知定性学习者 QLAP。 QLAP 在连续环境中自主学习有用的状态抽象和一组分层动作。 QLAP 中的学习是无监督的。代理从对世界的非常广泛的离散化开始（它只能判断变量的值是增加还是减少）。使用这种离散化，QLAP 创建了一组预测模型。最初，这些模型不是很可靠，但是对于每个模型，QLAP 都可以找到新的离散化来改进它。这些新的离散化导致更多模型创建感知循环，从而产生更准确的模型和更精细的离散化。然后将模型转换为一组分层操作。 |
| 课程简介: | This video presents an introduction to the Qualitative Learner of Action and Perception, QLAP. QLAP autonomously learns a useful state abstraction and a set of hierarchical actions in continuous environments. Learning in QLAP is unsupervised. The agent begins with a very broad discretization of the world (it can only tell if the values of variables are increasing or decreasing). Using this discretization, QLAP creates a set of predictive models. Initially, these models are not very reliable, but for each one QLAP can find new discretizations to improve it. These new discretizations lead to more models creating a perception loop that leads to more accurate models and a finer discretization. The models are then converted into a set of hierarchical actions. |
| 关 键 词: | 学习预测模型; 感知定性学习; 离散化改进 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-06-16：zyk |
| 最后编审: | 2021-06-16：zyk |
| 阅读次数: | 37 |