206,657 Hits in 5.1 sec

A Survey of Exploration Methods in Reinforcement Learning [article]

Susan Amin, Maziar Gomrokchi, Harsh Satija, Herke van Hoof, Doina Precup
2021 arXiv   pre-print
In this article, we provide a survey of modern exploration methods in (Sequential) reinforcement learning, as well as a taxonomy of exploration methods.  ...  Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments.  ...  In this survey, we present a more detailed categorization of exploration methods in reinforcement learning (see Figure 1 ).  ... 
arXiv:2109.00157v2 fatcat:dlqhzwxscnfbxpt2i6rp7ovp6i


Leslie Pack Kaelbling
1996 Machine Learning  
The problem of exploration in unknown environments is a crucial one for reinforcement learning.  ...  A crucial problem in reinforcement learning, as in other kinds of learning, is that of finding and using bias.  ... 
doi:10.1007/bf00114721 fatcat:vweynsjrh5hnpdpyj7zad75i6i

Towards Sample Efficient Reinforcement Learning

Yang Yu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this article, we share our understanding of the problem, and discuss possible ways to alleviate the sample cost of reinforcement learning, from the aspects of exploration, optimization, environment  ...  However, current reinforcement learning techniques are still suffer from requiring a huge amount of interaction data, which could result in unbearable cost in real-world applications.  ...  By reinforcement learning, an agent interacts with the environment, explores the unknown area, and learns a policy from the exploration data.  ... 
doi:10.24963/ijcai.2018/820 dblp:conf/ijcai/Yu18 fatcat:rhoz76vu2jfr3gc2zufhzhtppq

A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions [article]

Xiaocong Chen, Lina Yao, Julian McAuley, Guanglin Zhou, Xianzhi Wang
2021 arXiv   pre-print
In light of the emergence of deep reinforcement learning (DRL) in recommender systems research and several fruitful results in recent years, this survey aims to provide a timely and comprehensive overview  ...  of the recent trends of deep reinforcement learning in recommender systems.  ...  To the best of our knowledge, this the first comprehensive survey in deep reinforcement learning based recommender systems. • We present a taxonomy of the literature of deep reinforcement learning in recommender  ... 
arXiv:2109.03540v2 fatcat:5gwrbfcj3rc7jfkd54eseck5ga

Deep Learning – A first Meta-Survey of selected Reviews across Scientific Disciplines and their Research Impact [article]

Jan Egger, Antonio Pepe, Christina Gsaxner, Jianning Li
2020 arXiv   pre-print
With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-analysis of selected reviews on deep learning across different scientific disciplines  ...  These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years.  ...  Acknowledgements This work sees the funding of the Austrian Science Fund (FWF) KLI 678-B31: Additional Information Competing financial interests: The authors declare no competing financial interests  ... 
arXiv:2011.08184v1 fatcat:7eofypvqordn7i4o7qmtoaaydi

A Survey of Deep Reinforcement Learning in Video Games [article]

Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao
2019 arXiv   pre-print
In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties.  ...  Deep reinforcement learning (DRL) has made great achievements since proposed.  ...  Reinforcement learning Reinforcement learning is a kind of machine learning methods where agents learn the optimal policy by trial and error [12] .  ... 
arXiv:1912.10944v2 fatcat:fsuzp2sjrfcgfkyclrsyzflax4

A Survey of Multi-Task Deep Reinforcement Learning

Nelson Vithayathil Varghese, Qusay H. Mahmoud
2020 Electronics  
Undoubtedly, the inception of deep reinforcement learning has played a vital role in optimizing the performance of reinforcement learning-based intelligent agents with model-free based approaches.  ...  Although these methods could improve the performance of agents to a greater extent, they were mainly limited to systems that adopted reinforcement learning algorithms focused on learning a single task.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics9091363 fatcat:cohk2pukzbgbfizarqweuw45oe

A Survey on Recent Advances and Challenges in Reinforcement LearningMethods for Task-Oriented Dialogue Policy Learning [article]

Wai-Chung Kwan, Hongru Wang, Huimin Wang, Kam-Fai Wong
2022 arXiv   pre-print
Besides, we provide a comprehensive survey of applying RL to dialogue policy learning by categorizing recent methods into basic elements in RL.  ...  Dialogue Policy Learning is a key component in a task-oriented dialogue system (TDS) that decides the next action of the system given the dialogue state at each turn.  ...  More works are needed to explore efficient learning methods in TDS under the meta-learning paradigm.  ... 
arXiv:2202.13675v1 fatcat:ee5welwqhzax7aveuybjfzl66e

A survey of benchmarks for reinforcement learning algorithms

Belinda Stapelberg, Katherine Mary Malan
2020 South African Computer Journal  
\par The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner.  ...  Reinforcement learning has recently experienced increased prominence in the machine learning community.  ...  .: A survey of benchmarking frameworks for reinforcement learning Stapelberg, B. and Malan, K.M.: A survey of benchmarking frameworks for reinforcement learning  ... 
doi:10.18489/sacj.v32i2.746 fatcat:66fd47ejfbg6jcfykelm42klr4

Reinforcement Learning [chapter]

Shimon Whiteson
2010 Studies in Computational Intelligence  
In their article, "On the Analysis and Design of Software for Reinforcement Learning, with a Survey of Existing Systems", Kovacs and Egginton investigate practical issues involved in constructing software  ...  In "Characterizing Reinforcement Learning Methods through Parameterized Learning Problems", Kalyanakrishnan and Stone develop a parameterized class of reinforcementlearning problems and use it to conduct  ... 
doi:10.1007/978-3-642-13932-1_2 fatcat:mk42pvygnzhffp24oaqz6kh3qi

Introduction to the special issue on empirical evaluations in reinforcement learning

Shimon Whiteson, Michael L. Littman
2011 Machine Learning  
In their article, "On the Analysis and Design of Software for Reinforcement Learning, with a Survey of Existing Systems", Kovacs and Egginton investigate practical issues involved in constructing software  ...  In "Characterizing Reinforcement Learning Methods through Parameterized Learning Problems", Kalyanakrishnan and Stone develop a parameterized class of reinforcementlearning problems and use it to conduct  ... 
doi:10.1007/s10994-011-5255-6 fatcat:mywormeonzelxbksicouln2m2e

Self-Regulating Action Exploration in Reinforcement Learning

Teck-Hou Teng, Ah-Hwee Tan, Yuan-Sin Tan
2012 Procedia Computer Science  
In essence, the proposed method eliminates the guesswork on the amount of exploration needed during reinforcement learning.  ...  In addition, the change in exploration-exploitation rates alters the duration of the learning process.  ...  This project was conducted in close collaboration with Khee-Yin How and his team at DSO National Laboratories, Seng-Beng Ho and his team at Temasek Laboratories@NUS, Adrian Yeo and his team at CAE (S.E.A  ... 
doi:10.1016/j.procs.2012.09.110 fatcat:prvl7ykrt5ccpg73myaa2l53iy

From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN) [article]

Xin Ye, Yezhou Yang
2021 arXiv   pre-print
future research in these key areas worth exploring for the community.  ...  This survey first summarizes the representative work of learning-based approaches for the VIN task and then identifies and discusses lingering issues impeding the VIN performance, as well as motivates  ...  The other is the reinforcement learning method of taking the visual navigation task as a MDP problem.  ... 
arXiv:2002.11310v2 fatcat:jhcdhsntffer7a6725adbhzkke

Combining Local and Global Direct Derivative-Free Optimization for Reinforcement Learning

Matteo Leonetti, Petar Kormushev, Simone Sagratella
2012 Cybernetics and Information Technologies  
We consider the problem of optimization in policy space for reinforcement learning.  ...  While a plethora of methods have been applied to this problem, only a narrow category of them proved feasible in robotics.  ...  Introduction Reinforcement Learning (RL) is the learning paradigm in which an agent improves its behavior on a given task by exploring the environment through trial and error.  ... 
doi:10.2478/cait-2012-0021 fatcat:p327z33c7jhmvdlwzazbptqxny

Reinforcement Learning: A Survey

L. P. Kaelbling, M. L. Littman, A. W. Moore
1996 The Journal of Artificial Intelligence Research  
It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.  ...  This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning.  ...  Also thanks to our many colleagues in the reinforcement-learning community who have done this work and explained it to us.  ... 
doi:10.1613/jair.301 fatcat:nbo23vmu6rfz3ctpjbk7sdcnt4
« Previous Showing results 1 — 15 out of 206,657 results