کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
405585 677681 2010 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Efficient exploration through active learning for value function approximation in reinforcement learning
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Efficient exploration through active learning for value function approximation in reinforcement learning
چکیده انگلیسی

Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares policy iteration (LSPI) framework allows us to employ statistical active learning methods for linear regression. Then we propose a design method of good sampling policies for efficient exploration, which is particularly useful when the sampling cost of immediate rewards is high. The effectiveness of the proposed method, which we call active policy iteration (API), is demonstrated through simulations with a batting robot.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 23, Issue 5, June 2010, Pages 639–648
نویسندگان
, , ,