20,883 Hits in 5.8 sec

Evolutionary Dynamics of Multi-Agent Learning: A Survey

Daan Bloembergen, Karl Tuyls, Daniel Hennes, Michael Kaisers
2015 The Journal of Artificial Intelligence Research  
The paper provides a roadmap on the progress that has been achieved in analysing the evolutionary dynamics of multi-agent learning by highlighting the main results and accomplishments.  ...  The past two decades have seen the emergence of reinforcement learning, both in single and multi-agent settings, as a strong, robust and adaptive learning paradigm.  ...  Acknowledgments We are grateful to the editor and anonymous reviewers of JAIR for their valuable feedback and helpful suggestions.  ... 
doi:10.1613/jair.4818 fatcat:6wqvs63nezd6xfz3zf7c4cattq

Evolutionary Machine Learning: A Survey

Akbar Telikani, Amirhessam Tahmassebi, Wolfgang Banzhaf, Amir H. Gandomi
2022 ACM Computing Surveys  
We do not provide a comprehensive review of evolutionary ML approaches here; instead, we discuss how EC algorithms can contribute to ML by addressing conventional challenges of the artificial intelligence  ...  Evolutionary Computation (EC) approaches are inspired by nature and solve optimization problems in a stochastic manner.  ...  Evolutionary Machine Learning: A Survey 161:25 The use of multi-objective approaches in the optimization of neural networks and deep learning can further balance accuracy with generalization.  ... 
doi:10.1145/3467477 fatcat:o6m3nekqfnaudjnxxoeferhine

A Survey on Computational Intelligence-based Transfer Learning [article]

Mohamad Zamini, Eunjin Kim
2022 arXiv   pre-print
The goal of transfer learning (TL) is providing a framework for exploiting acquired knowledge from source to target data.  ...  Transfer learning approaches compared to traditional machine learning approaches are capable of modeling better data patterns from the current domain.  ...  They used a learning method named a multi-agent reinforcement learning algorithm which does self-trades.  ... 
arXiv:2206.10593v1 fatcat:n4bofmrgs5eidciu6b3p3gcxey

Curriculum Learning: A Survey [article]

Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe
2022 arXiv   pre-print
We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria.  ...  Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks.  ...  Milano and Nolfi (2021) apply curriculum learning over the evolutionary training of embodied agents.  ... 
arXiv:2101.10382v3 fatcat:doognr7ggfaalg7kd2i3n7s3jy

Learning classifier systems: a survey

Olivier Sigaud, Stewart W. Wilson
2007 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
At the origin of Holland's work, LCSs were seen as a model of the emergence of cognitive abilities thanks to adaptive mechanisms, particularly evolutionary processes.  ...  Indeed, from a Reinforcement Learning point of view, LCSs can be seen as learning systems building a compact representation of their problem thanks to generalization.  ...  Recently, a surge of interest on the discovery of complex 'building blocks' in the structure of input data led to a more frequent use of multi-point crossover.  ... 
doi:10.1007/s00500-007-0164-0 fatcat:yaa6csslmfavdilydz3zahgqka

Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey [article]

Olivier Sigaud
2022 arXiv   pre-print
Deep neuroevolution and deep Reinforcement Learning have received a lot of attention in the last years.  ...  In this paper, we provide a survey of this emerging trend by organizing the literature into related groups of works and casting all the existing combinations in each group into a generic framework.  ...  Instead of evolving a population of agents, the eQ algorithm (Leite et al., 2020) evolves a population of critics, which are fixed over the course of learning for a given agent.  ... 
arXiv:2203.14009v5 fatcat:5vqkpzmmmvfvpgifnnd4hoxtle

Multi-agent deep reinforcement learning: a survey

Sven Gronauer, Klaus Diepold
2021 Artificial Intelligence Review  
This article provides an overview of the current developments in the field of multi-agent deep reinforcement learning.  ...  We focus primarily on literature from recent years that combines deep reinforcement learning methods with a multi-agent scenario.  ...  In this article, we surveyed recent works that combine deep learning methods with multi-agent reinforcement learning.  ... 
doi:10.1007/s10462-021-09996-w fatcat:blu4ekwaxjfo5it3y7taqnzq4a

Reinforcement Learning in Healthcare: A Survey [article]

Chao Yu, Jiming Liu, Shamim Nemati
2020 arXiv   pre-print
As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback  ...  domains that have infiltrated many aspects of a healthcare system.  ...  Being a sequential evolutionary process by nature, cancer treatment is a major objective of RL in DTR applications [102] , [103] .  ... 
arXiv:1908.08796v4 fatcat:iqqe3jifqvfntmxr6cakl4p2fy

Quantum Optimization and Quantum Learning: A Survey

Yangyang Li, Mengzhuo Tian, Guangyuan Liu, Cheng Peng, Licheng Jiao
2020 IEEE Access  
It is a frontier interdisciplinary subject with a perfect integration of biology, mathematics and other disciplines.  ...  INDEX TERMS Quantum optimization, quantum learning, quantum evolutionary algorithm (QEA), quantum particle swarm algorithm (QPSO), quantum immune clonal algorithm (QICA), quantum neural network (QNN),  ...  Network in [136] are presented as quantum computational agents, which have learning ability via implementing reinforcement learning algorithm.  ... 
doi:10.1109/access.2020.2970105 fatcat:y765erlnyzakvdj3nv273ccgei

Model-based Reinforcement Learning: A Survey [article]

Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker
2022 arXiv   pre-print
Altogether, the survey presents a broad conceptual overview of the combination of planning and learning for MDP optimization.  ...  Two key approaches to this problem are reinforcement learning (RL) and planning. This paper presents a survey of the integration of both fields, better known as model-based reinforcement learning.  ...  Therefore, this article presents a survey of the combination of planning and learning.  ... 
arXiv:2006.16712v4 fatcat:qyb4auoqovdeji4ov65sv6f3fq

Collective Intelligence for Deep Learning: A Survey of Recent Developments [article]

David Ha, Yujin Tang
2022 arXiv   pre-print
We hope this review can serve as a bridge between the complex systems and deep learning communities.  ...  In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence.  ...  connections with other neurons in the system, hence the problem of learning to learn is treated as a multi-agent RL problem where each agent is part of the collection of neurons in a neural network.  ... 
arXiv:2111.14377v3 fatcat:dg5uvn7mt5g5ncgtrzw3a3ul4y

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey [article]

Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer
2022 arXiv   pre-print
Developmental approaches argue that this can only be achieved by autotelic agents: intrinsically motivated learning agents that can learn to represent, generate, select and solve their own problems.  ...  In recent years, the convergence of developmental approaches with deep reinforcement learning (RL) methods has been leading to the emergence of a new field: developmental reinforcement learning.  ...  With successor features, the Q-value of a goal can be expressed as a linear combination of learned reward features, efficiently decoupling the rewards from the environmental dynamics.  ... 
arXiv:2012.09830v7 fatcat:lyqugbwznratfgtgstrjql4qja

A Survey of Planning and Learning in Games

Fernando Fradique Duarte, Nuno Lau, Artur Pereira, Luis Paulo Reis
2020 Applied Sciences  
This paper presents a survey of the multiple methodologies that have been proposed to integrate planning and learning in the context of games.  ...  In general, games pose interesting and complex problems for the implementation of intelligent agents and are a popular domain in the study of artificial intelligence.  ...  multi-agent environments.  ... 
doi:10.3390/app10134529 fatcat:wc27eo2wmvd6lclar7yteyj6cm

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey [article]

Sanmit Narvekar and Bei Peng and Matteo Leonetti and Jivko Sinapov and Matthew E. Taylor and Peter Stone
2020 arXiv   pre-print
In this article, we present a framework for curriculum learning (CL) in reinforcement learning, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals  ...  Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback.  ...  Part of this work has taken place in the Learning Agents Research Group (LARG) at the Artificial Intelligence Laboratory, The University of Texas at Austin. LARG re-  ... 
arXiv:2003.04960v2 fatcat:iacmqeb7jjeezpo27jsnzuqb7u

A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions [article]

Amit Kumar Mondal
2020 arXiv   pre-print
The fundamental objective of this paper is to provide a framework for the presentation of available methods of reinforcement learning that is informative enough and simple to follow for the new researchers  ...  In this paper, we present a comprehensive study on Reinforcement Learning focusing on various dimensions including challenges, the recent development of different state-of-the-art techniques, and future  ...  Problems to solve: Can learn directly from the raw experience without a model of the dynamics of the environment. Techniques: Mainly based on Monte Carlo methods and dynamic programming [19] .  ... 
arXiv:2001.06921v2 fatcat:uwqn4jmginf73ouk3zmm45uozy
« Previous Showing results 1 — 15 out of 20,883 results