کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
410994 679175 2006 9 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Parallel reinforcement learning using multiple reward signals
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Parallel reinforcement learning using multiple reward signals
چکیده انگلیسی

Reinforcement learning is a quite general learning paradigm that can be used to solve a large set of problems. For complex problems it has been shown that by using task decomposition it may be possible for the system to learn faster. One common approach is to construct systems with multiple modules, where each module learns a sub-task. We present a parallel learning method for agents with an actor–critic architecture based on artificial neural networks. The agents have multiple modules, where the modules can learn in parallel to further increase learning speed. Each module solves a sub-problem and receives its own separate reward signal with all modules trained concurrently. We use the method on a grid world navigation task and show that parallel learning can significantly reduce learning time.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 69, Issues 16–18, October 2006, Pages 2171–2179
نویسندگان
,