scholarly journals The evolution of continuous learning of the structure of the environment

2014 ◽  
Vol 11 (92) ◽  
pp. 20131091 ◽  
Author(s):  
Oren Kolodny ◽  
Shimon Edelman ◽  
Arnon Lotem
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Language Acquisition ◽  
Learning Strategies ◽  
Computer Simulations ◽  
The Other ◽  
Continuous Learning ◽  
Agent Based ◽  
Statistical Regularities ◽  
Learning Reinforcement

Continuous, ‘always on’, learning of structure from a stream of data is studied mainly in the fields of machine learning or language acquisition, but its evolutionary roots may go back to the first organisms that were internally motivated to learn and represent their environment. Here, we study under what conditions such continuous learning (CL) may be more adaptive than simple reinforcement learning and examine how it could have evolved from the same basic associative elements. We use agent-based computer simulations to compare three learning strategies: simple reinforcement learning; reinforcement learning with chaining (RL-chain) and CL that applies the same associative mechanisms used by the other strategies, but also seeks statistical regularities in the relations among all items in the environment, regardless of the initial association with food. We show that a sufficiently structured environment favours the evolution of both RL-chain and CL and that CL outperforms the other strategies when food is relatively rare and the time for learning is limited. This advantage of internally motivated CL stems from its ability to capture statistical patterns in the environment even before they are associated with food, at which point they immediately become useful for planning.

scholarly journals Quantum-accessible reinforcement learning beyond strictly epochal environments

2021 ◽  
Vol 3 (2) ◽  
Author(s):  
A. Hamann ◽  
V. Dunjko ◽  
S. Wölk
Keyword(s):  
Machine Learning ◽  
Quantum Theory ◽  
Reinforcement Learning ◽  
Figure Of Merit ◽  
Quantum Algorithms ◽  
Learning Reinforcement ◽  
Changes Over Time ◽  
Amplitude Amplification ◽  
Grover Iterations ◽  
Over Time

AbstractIn recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work, we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups. In addition, we prove that an algorithm based on Grover iterations is optimal for oracle identification even if the oracle changes over time in a way that the “rewarded space” is monotonically increasing. This result constitutes one of the first generalizations of quantum-accessible reinforcement learning.

Machine Learning (Reinforcement Learning)-Based Steel Stock Yard Planning Algorithm

2020 ◽  
Author(s):  
Jong Hun Woo ◽  
Young In Cho ◽  
Sang Hyeon Yu ◽  
So Hyun Nam ◽  
Haoyu Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Planning Algorithm ◽  
Learning Reinforcement ◽  
Yard Planning

MAITS

2011 ◽  
pp. 189-208 ◽  
Author(s):  
Dharmendra Sharma
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Learning Algorithm ◽  
Computer Forensics ◽  
The Other ◽  
Security Requirements ◽  
Machine Learning Algorithm ◽  
Agent Based ◽  
Authentication And Authorization ◽  
Multi Agent

In this chapter, we propose a multi-agent-based information technology (IT) security approach (MAITS) as a holistic solution to the increasing needs of securing computer systems. Each specialist task for security requirements is modeled as a specialist agent. MAITS has five groups of working agents—administration assistant agents, authentication and authorization agents, system log *monitoring agents, intrusion detection agents, and pre-mortem-based computer forensics agents. An assessment center, which is comprised of yet another special group of agents, plays a key role in coordinating the interaction of the other agents. Each agent has an agent engine of an appropriate machine-learning algorithm. The engine enables the agent with learning, reasoning, and decision-making abilities. Each agent also has an agent interface, through which the agent interacts with other agents and also the environment.

scholarly journals Aprender como una máquina: introduciendo la Inteligencia Artificial en la enseñanza secundaria

2021 ◽  
Vol 14 (1) ◽  
pp. 5
Author(s):  
J.M. Calabuig ◽  
L.M. Garcia-Raffi ◽  
E.A. Sánchez-Pérez
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Learning Reinforcement ◽  
Sobre Todo

<p class="p1">La inteligencia artificial está presente en el entorno habitual de todos los estudiantes de secundaria. Sin embargo, la población general -y los alumnos en particular- no conocen cómo funcionan estas técnicas algorítmicas, que muchas veces tienen mecanismos muy sencillos y que pueden explicarse a nivel elemental en las clases de matemáticas o de tecnología en los Institutos de Enseñanza Secundaria (IES). Posiblemente estos contenidos tardarán muchos años en formar parte de los currículos de estas asignaturas, pero se pueden introducir como parte de los contenidos de álgebra que se explican en matemáticas, o de los relacionados con los algoritmos, en las clases de informática. Sobre todo si se plantean en forma de juego, en los que pueden competir diferentes grupos de estudiantes, tal y como proponemos en este artículo. Así, presentamos un ejemplo muy simple de un algoritmo de aprendizaje por refuerzo (Machine Learning-Reinforcement Learning), que sintetiza en una actividad lúdica los elementos fundamentales que constituyen un algoritmo de inteligencia artificial.</p>

scholarly journals Developmental Language Learning from Human/Humanoid Robot Social Interactions

Robotics ◽  
2013 ◽  
pp. 1328-1353 ◽  
Author(s):  
Artur M. Arsénio
Keyword(s):  
Machine Learning ◽  
Social Context ◽  
Language Acquisition ◽  
Language Learning ◽  
Learning Strategies ◽  
Learning Process ◽  
Computational Models ◽  
Robot Learning ◽  
Psychological Models

This chapter presents work on developmental machine learning strategies applied to robots for language acquisition. The authors focus on learning by scaffolding and emphasize the role of the human caregiver for robot learning. Indeed, language acquisition does not occur in isolation, neither can it be a robot’s “genetic legacy.” Rather, they propose that language is best acquired incrementally, in a social context, through human-robot interactions in which humans guide the robot, as if it were a child, through the learning process. The authors briefly discuss psychological models related to this work and describe and discuss computational models that they implemented for robot language acquisition. The authors aim to introduce robots into our society and treat them as us, using child development as a metaphor for robots’ developmental language learning.

scholarly journals Pemanfaatan Machine Learning dalam Berbagai Bidang: Review paper

2020 ◽  
Vol 5 (1) ◽  
Author(s):  
Ahmad Roihan ◽  
Po Abas Sunarya ◽  
Ageng Setiani Rafika
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Reinforcement Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Review Paper ◽  
Computational Costs ◽  
Accuracy And Precision ◽  
Learning Reinforcement ◽  
High Level

Abstrak - Pembelajaran mesin merupakan bagian dari kecerdasan buatan yang banyak digunakan untuk memecahkan berbagai masalah. Artikel ini menyajikan ulasan pemecahan masalah dari penelitian-penelitian terkini dengan mengklasifikasikan machine learning menjadi tiga kategori: pembelajaran terarah, pembelajaran tidak terarah, dan pembelajaran reinforcement. Hasil ulasan menunjukkan ketiga kategori masih berpeluang digunakan dalam beberapa kasus terkini dan dapat ditingkatkan untuk mengurangi beban komputasi dan mempercepat kinerja untuk mendapatkan tingkat akurasi dan presisi yang tinggi. Tujuan ulasan artikel ini diharapkan dapat menemukan celah dan dijadikan pedoman untuk penelitian pada masa yang akan datang.Katakunci: pembelajaran mesin, pembelajaran reinforcement, pembelajaran terarah, pembelajaran tidak terarahAbstract - Machine learning is part of artificial intelligence that is widely used to solve various problems. This article reviews problem solving from the latest studies by classifying machine learning into three categories: supervised learning, unsupervised learning, and reinforcement learning. The results of the review show that the three categories are still likely to be used in some of the latest cases and can be improved to reduce computational costs and accelerate performance to get a high level of accuracy and precision. The purpose of this article review is expected to be able to find a gap and it is used as a guideline for future research.Keywords: machine learning, reinforcement learning, supervised learning, unsupervised learning

scholarly journals Towards Computer Simulations of Virtue Ethics

2019 ◽  
Vol 2 (1) ◽  
pp. 399-413
Author(s):  
Jeremiah A. Lasquety-Reyes
Keyword(s):  
Computer Simulation ◽  
Virtue Ethics ◽  
Computer Simulations ◽  
Agent Based Modeling ◽  
The Other ◽  
Single Variable ◽  
Agent Based ◽  
Internal Struggle ◽  
Cardinal Virtue ◽  
Social Components

AbstractThis article presents two approaches for computer simulations of virtue ethics in the context of agent-based modeling, a simple way and a complex way. The simple way represents virtues as numeric variables that are invoked in specific events or situations. This way can easily be implemented and included in social simulations. On the other hand, the complex way requires a PECS framework: physical, cognitive, emotional, and social components need to be implemented in agents. Virtue is the result of the interaction of these internal components rather than a single variable. I argue that the complex way using the PECS framework is more suitable for simulating virtue ethics theory because it can capture the internal struggle and conflict sometimes involved in the practice of virtue. To show how the complex way could function, I present a sample computer simulation for the cardinal virtue of temperance, the virtue that moderates physical desires such as food, drink, and sex. This computer simulation is programmed in Python and builds upon the well-known Sugarscape simulation.1

Developmental Language Learning from Human/Humanoid Robot Social Interactions

2013 ◽  
pp. 197-223
Author(s):  
Artur M. Arsénio
Keyword(s):  
Machine Learning ◽  
Social Context ◽  
Language Acquisition ◽  
Language Learning ◽  
Learning Strategies ◽  
Learning Process ◽  
Computational Models ◽  
Robot Learning ◽  
Psychological Models

This chapter presents work on developmental machine learning strategies applied to robots for language acquisition. The authors focus on learning by scaffolding and emphasize the role of the human caregiver for robot learning. Indeed, language acquisition does not occur in isolation, neither can it be a robot’s “genetic legacy.” Rather, they propose that language is best acquired incrementally, in a social context, through human-robot interactions in which humans guide the robot, as if it were a child, through the learning process. The authors briefly discuss psychological models related to this work and describe and discuss computational models that they implemented for robot language acquisition. The authors aim to introduce robots into our society and treat them as us, using child development as a metaphor for robots’ developmental language learning.

Sign in / Sign up

Export Citation Format

Share Document