scholarly journals Air holding problem solving with reinforcement learning to reduce airspace congestion

2014 ◽  
Vol 49 (5) ◽  
pp. 616-633 ◽  
Author(s):  
Leonardo L. B. V. Cruciol ◽  
Li Weigang ◽  
Alexandre Gomes de Barros ◽  
Marlon Winston Koendjbiharie
Keyword(s):  
Reinforcement Learning ◽  
Problem Solving

scholarly journals Analyzing the Effects of Reinforcement Learning to Develop Humanoid Robots

2019 ◽  
Vol 8 (1) ◽  
pp. 55-66
Author(s):  
Naaima Suroor ◽  
Imran Hussain ◽  
Aqeel Khalique ◽  
Tabrej Ahamad Khan
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Problem Solving ◽  
Cognitive Abilities ◽  
Humanoid Robots ◽  
Human Intervention ◽  
Learning Techniques ◽  
Probable Impact ◽  
Learning Concept

Reinforcement learning is a flourishing machine learning concept that has greatly influenced how robots are designed and taught to solve problems without human intervention. Robotics is not an alien discipline anymore, and we have several great innovations in this field that promise to impact lives for the better. However, humanoid robots are still a baffling concept for scientists, although we have managed to develop a few great inventions which look, talk, work, and behave very similarly to humans. But, can these machines actually exhibit the cognitive abilities of judgment, problem-solving, and perception as well as humans? In this article, the authors analyzed the probable impact and aspects of robots and their potential to behave like humans in every possible way through reinforcement learning techniques. The paper also discusses the gap between 'natural' and 'artificial' knowledge.

scholarly journals Adaptive Human–Machine Evaluation Framework Using Stochastic Gradient Descent-Based Reinforcement Learning for Dynamic Competing Network

2020 ◽  
Vol 10 (7) ◽  
pp. 2558 ◽  
Author(s):  
Jinbae Kim ◽  
Hyunsoo Lee
Keyword(s):  
Reinforcement Learning ◽  
Problem Solving ◽  
Special Problem ◽  
Evaluation Framework ◽  
Stochastic Gradient Descent ◽  
Human Evaluation ◽  
Basketball Game ◽  
Network Topologies ◽  
Multiple Network ◽  
Considerable Work

Complex problems require considerable work, extensive computation, and the development of effective solution methods. Recently, physical hardware- and software-based technologies have been utilized to support problem solving with computers. However, problem solving often involves human expertise and guidance. In these cases, accurate human evaluations and diagnoses must be communicated to the system, which should be done using a series of real numbers. In previous studies, only binary numbers have been used for this purpose. Hence, to achieve this objective, this paper proposes a new method of learning complex network topologies that coexist and compete in the same environment and interfere with the learning objectives of the others. Considering the special problem of reinforcement learning in an environment in which multiple network topologies coexist, we propose a policy that properly computes and updates the rewards derived from quantitative human evaluation and computes together with the rewards of the system. The rewards derived from the quantitative human evaluation are designed to be updated quickly and easily in an adaptive manner. Our new framework was applied to a basketball game for validation and demonstrated greater effectiveness than the existing methods.

scholarly journals Hierarchical reinforcement learning as creative problem solving

2016 ◽  
Vol 86 ◽  
pp. 196-206 ◽  
Author(s):  
Thomas R. Colin ◽  
Tony Belpaeme ◽  
Angelo Cangelosi ◽  
Nikolas Hemion
Keyword(s):  
Reinforcement Learning ◽  
Problem Solving ◽  
Creative Problem Solving ◽  
Hierarchical Reinforcement Learning ◽  
Creative Problem
Sign in / Sign up

Export Citation Format

Share Document