Special Issue "Advances in Reinforcement Learning"

A special issue of Machine Learning and Knowledge Extraction (ISSN 2504-4990). This special issue belongs to the section "Learning".

Deadline for manuscript submissions: closed (15 March 2022) | Viewed by 5072

Special Issue Editor

Prof. Dr. Ausif Mahmood
E-Mail Website
Guest Editor
Chair, Department of Computer Science and Engineering, Professor of Computer Science and Engineering, and Electrical Engineering, University of Bridgeport, Bridgeport, CT 06604, USA
Interests: deep learning; reinforcement learning; computer vision; NLP; optimization

Special Issue Information

Dear Colleagues,

Reinforcement Learning (RL), in which the agents learn by interacting with the environment, is one of the most exciting areas of Artificial Intelligence. Unlike other AI paradigms of supervised and unsupervised learning, no predisposed intuition, data, or supervision is necessary in RL. Starting from the foundational work of the Bellman equations, many RL algorithms have been proposed in the last few years, and the success of RL has been demonstrated in many practical applications in the fields of robotics, autonomous vehicles, communication systems, game playing, finance, healthcare, adaptive decision control, among others. Even though considerable work on algorithmic and mathematical formulations related to single-agent RL systems has led to impressive results in different domains, Multi-Agent RL (MARL) is still in its infancy. Some of the challenges yet to be resolved, both for single- and Multi-Agent RL systems, include real-time adaptation to nonstationary or stochastic environments, high-dimensional continuous state and action spaces, adversarial RL including both attacks and defenses, partial observability of the environment, RL under interference or noisy environments, and safety control. To provide some of the solutions to the challenging problems of RL, we propose this Special Issue on “Advances in Reinforcement Learning”. With this aim, we invite papers in both theoretical and applied research areas related to RL and MARL. We believe this Special Issue will contribute to advancing the state of the art in reinforcement learning.

Prof. Dr. Ausif Mahmood
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machine Learning and Knowledge Extraction is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • reinforcement learning
  • multi-agent reinforcement learning
  • Markov decision process
  • value iteration
  • policy gradients
  • learning to learn
  • deep Q learning
  • Markov game
  • deep reinforcement learning

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Review

Review
Robust Reinforcement Learning: A Review of Foundations and Recent Advances
Mach. Learn. Knowl. Extr. 2022, 4(1), 276-315; https://doi.org/10.3390/make4010013 - 19 Mar 2022
Viewed by 1162
Abstract
Reinforcement learning (RL) has become a highly successful framework for learning in Markov decision processes (MDP). Due to the adoption of RL in realistic and complex environments, solution robustness becomes an increasingly important aspect of RL deployment. Nevertheless, current RL algorithms struggle with [...] Read more.
Reinforcement learning (RL) has become a highly successful framework for learning in Markov decision processes (MDP). Due to the adoption of RL in realistic and complex environments, solution robustness becomes an increasingly important aspect of RL deployment. Nevertheless, current RL algorithms struggle with robustness to uncertainty, disturbances, or structural changes in the environment. We survey the literature on robust approaches to reinforcement learning and categorize these methods in four different ways: (i) Transition robust designs account for uncertainties in the system dynamics by manipulating the transition probabilities between states; (ii) Disturbance robust designs leverage external forces to model uncertainty in the system behavior; (iii) Action robust designs redirect transitions of the system by corrupting an agent’s output; (iv) Observation robust designs exploit or distort the perceived system state of the policy. Each of these robust designs alters a different aspect of the MDP. Additionally, we address the connection of robustness to the risk-based and entropy-regularized RL formulations. The resulting survey covers all fundamental concepts underlying the approaches to robust reinforcement learning and their recent advances. Full article
(This article belongs to the Special Issue Advances in Reinforcement Learning)
Show Figures

Figure 1

Review
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Mach. Learn. Knowl. Extr. 2022, 4(1), 172-221; https://doi.org/10.3390/make4010009 - 17 Feb 2022
Viewed by 1121
Abstract
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount [...] Read more.
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions in order to tackle these challenges, while simultaneously paving the road for behavior reuse and increased interpretability of RL systems. In this survey paper we first introduce a selection of problem-specific approaches, which provided insight in how to utilize often handcrafted abstractions in specific task settings. We then introduce the Options framework, which provides a more generic approach, allowing abstractions to be discovered and learned semi-automatically. Afterwards we introduce the goal-conditional approach, which allows sub-behaviors to be embedded in a continuous space. In order to further advance the development of HRL agents, capable of simultaneously learning abstractions and how to use them, solely from interaction with complex high dimensional environments, we also identify a set of promising research directions. Full article
(This article belongs to the Special Issue Advances in Reinforcement Learning)
Show Figures

Figure 1

Review
Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems: Part 1—Fundamentals and Applications in Games, Robotics and Natural Language Processing
Mach. Learn. Knowl. Extr. 2021, 3(3), 554-581; https://doi.org/10.3390/make3030029 - 15 Jul 2021
Cited by 1 | Viewed by 1952
Abstract
The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems. Reinforcement Learning (RL) is an approach to simulate the human’s natural learning process, [...] Read more.
The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems. Reinforcement Learning (RL) is an approach to simulate the human’s natural learning process, whose key is to let the agent learn by interacting with the stochastic environment. The fact that the agent has limited access to the information of the environment enables AI to be applied efficiently in most fields that require self-learning. Although efficient algorithms are being widely used, it seems essential to have an organized investigation—we can make good comparisons and choose the best structures or algorithms when applying DRL in various applications. In this overview, we introduce Markov Decision Processes (MDP) problems and Reinforcement Learning and applications of DRL for solving POMDP problems in games, robotics, and natural language processing. A follow-up paper will cover applications in transportation, communications and networking, and industries. Full article
(This article belongs to the Special Issue Advances in Reinforcement Learning)
Show Figures

Figure 1

Back to TopTop