State-Action Space Construction for Multi-Layered Learning System.
نویسندگان
چکیده
منابع مشابه
State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action
This paper proposes a method which estimates the relationships between learner's behaviors and other agents' ones in the environment through interactions (observation and action) using the method of system identi cation. In order to identify the model of each agent, Akaike's Information Criterion is applied to the results of Canonical Variate Analysis for the relationship between the observed d...
متن کاملA Reinforcement Learning System Based on State Space Construction Using Fuzzy ART A Reinforcement Learning System Based on State Space Construction Using Fuzzy ART
A new reinforcement learning system using fuzzy ART (adaptive resonance theory) is proposed. In the proposed method, fuzzy ART is used to classify observed information and to construct effective state space. Then, profit sharing is employed as a reinforcement learning method. Furthermore, the proposed system is extended to the hierarchical structures for solving partially observable Markov deci...
متن کاملVision Based State Space Construction for Learning Mobile Robots in Multi-agent Environments
State space construction is one of the most fundamental issues for the reinforcement learning methods to be applied to real robot tasks because they need a well-defined state space so that they can converge correctly. Especially in multi-agent environments, the problem becomes more difficult since visual information observed by the learning robot seems irrelevant to its self motion due to actio...
متن کاملMulti-Layered Learning System for Real Robot Behavior Acquisition
This paper presents a series of the studies of multilayered learning system for vision-based behavior acquisition of a real mobile robot. The work of this system aims at building an autonomous robot which is able to develop its knowledge and behaviors from low level to higher one through the interaction with the environment in its life. The system creates leaning modules with small limited reso...
متن کاملAction Dependent State Space Abstraction for Hierarchical Learning Systems
To operate effectively in complex environments learning agents have to selectively ignore irrelevant details by forming useful abstractions. In this paper we outline a formulation of abstraction for reinforcement learning approaches to stochastic decision problems by extending one of the recent minimization models, known as ǫ-reduction. The technique presented here extends ǫ-reduction to SMDPs ...
متن کاملذخیره 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 the Robotics Society of Japan
سال: 2003
ISSN: 0289-1824,1884-7145
DOI: 10.7210/jrsj.21.164