0
喜欢
0
书签
声明论文
Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks   
摘  要:   Approximate Policy Iteration (API) is a reinforcement learn- ing paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for the closed-loop learning of map- pings from images to actions. This approach requires a family of function approximators that maps visual percepts to a real-valued function. For this purpose, we use Regression Extra-Trees, a fast, yet accurate and versatile machine learning algorithm. The inputs of the Extra-Trees con- sist of a set of visual features that digest the informative patterns in the visual signal. We also show how to parallelize the Extra-Tree learn- ing process to further reduce the computational expense, which is often essential in visual tasks. Experimental results on real-world images are given that indicate that the combination of API with Extra-Trees is a promising framework for the interactive learning of visual tasks.
发  表:   The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases  2006

论文统计图
共享有8个版本
 [展开全部版本] 

Bibtex
创新指数 
阅读指数 
重现指数 
论文点评
还没有人点评哦

Feedback
Feedback
Feedback
我想反馈:
排行榜