Tidy-up Task Planner based on Q-learning

نویسندگان
چکیده

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Hierarchical Task-Network Planner based on Symbolic Model Checking

Although several approaches have been developed for planning in nondeterministic domains, solving large planning problems is still quite difficult. In this work, we present a novel algorithm, called YoYo, for planning in nondeterministic domains under the assumption of full observability. This algorithm enables us to combine the power of search-control strategies as in Planning with Hierarchica...

متن کامل

On P4-tidy graphs

We study the P4-tidy graphs, a new class defined by Rusu [30] in order to illustrate the notion of P4-domination in perfect graphs. This class strictly contains the P4-extendible graphs and the P4-lite graphs defined by Jamison & Olariu in [19] and [23] and we show that the P4-tidy graphs and P4-lite graphs are closely related. Note that the class of P4-lite graphs is a class of brittle graphs ...

متن کامل

The SelMax Planner: Online Learning for Speeding up Optimal Planning∗

The SelMax planner combines two state-of-the-art admissible heuristics using an online learning approach. In this paper we describe the online learning approach employed by SelMax, briefly review the Fast Downward framework, and describe

متن کامل

An Adaptive Planner Based on Learning of Planning Performance

Case-based planners often face the problem of incurring more computational cost for retrieving and modifying a case for reuse, than what can be saved by reusing the case. We present a case-based planning system that learns the performance of a given planner (called the default planner) in a training phase, and exploits this knowledge to retrieve and reuse cases such that planning effort is save...

متن کامل

Connectionist Q-learning in Robot Control Task

The Q-Learning algorithm suggested by Watkins in 1989 [1] belongs to a group of reinforcement learning algorithms. Reinforcement learning in robot control tasks has the form of multi-step procedure of adaptation. The main feature of that technique is that in the process of learning the system is not shown how to act in a specific situation. Instead, learning develops by trial and error using re...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of Korea Robotics Society

سال: 2021

ISSN: 1975-6291,2287-3961

DOI: 10.7746/jkros.2021.16.1.056