You are currently viewing a new version of our website. To view the old version click .

Algorithms, Volume 15, Issue 3

March 2022 - 30 articles

Cover Story: Reinforcement learning (RL) with sparse rewards is still an open challenge. Classic methods rely on learning via extrinsic rewards, and in situations where these are sparse, the agent may not learn at all. Similarly, if the agent gets rewards that create suboptimal modes of the objective function, it will prematurely stop exploring. Recent methods add intrinsic rewards to encourage exploration, but they lead to a non-stationary target for the Q-function. In this paper, we present a novel approach that (1) plans exploration far into the future using a long-term visit count and (2) decouples exploration and exploitation by learning a separate function. We also propose new environments for benchmarking exploration in RL. Results show that our approach outperforms existing methods. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles (30)

  • Review
  • Open Access
4 Citations
4,492 Views
14 Pages

Non-Invasive Systems and Methods Patents Review Based on Electrocardiogram for Diagnosis of Cardiovascular Diseases

  • Nellyzeth Flores,
  • Marco A. Reyna,
  • Roberto L. Avitia,
  • Jose Antonio Cardenas-Haro and
  • Conrado Garcia-Gonzalez

28 February 2022

Cardiovascular disease (CVD) is a global public health problem. It is a disease of multifactorial origin, and with this characteristic, having an accurate diagnosis of its incidence is a problem that health personnel face every day. That is why havin...

  • Article
  • Open Access
6 Citations
4,500 Views
44 Pages

Long-Term Visitation Value for Deep Exploration in Sparse-Reward Reinforcement Learning

  • Simone Parisi,
  • Davide Tateo,
  • Maximilian Hensel,
  • Carlo D’Eramo,
  • Jan Peters and
  • Joni Pajarinen

28 February 2022

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all....

  • Article
  • Open Access
1 Citations
3,765 Views
20 Pages

An Effective Algorithm for Finding Shortest Paths in Tubular Spaces

  • Dang-Viet-Anh Nguyen,
  • Jérôme Szewczyk and
  • Kanty Rabenorosoa

25 February 2022

We propose a novel algorithm to determine the Euclidean shortest path (ESP) from a given point (source) to another point (destination) inside a tubular space. The method is based on the observation data of a virtual particle (VP) assumed to move alon...

  • Article
  • Open Access
7 Citations
4,143 Views
37 Pages

25 February 2022

The Expectation Maximisation (EM) algorithm is widely used to optimise non-convex likelihood functions with latent variables. Many authors modified its simple design to fit more specific situations. For instance, the Expectation (E) step has been rep...

  • Article
  • Open Access
11 Citations
5,474 Views
16 Pages

Prediction of Injuries in CrossFit Training: A Machine Learning Perspective

  • Serafeim Moustakidis,
  • Athanasios Siouras,
  • Konstantinos Vassis,
  • Ioannis Misiris,
  • Elpiniki Papageorgiou and
  • Dimitrios Tsaopoulos

24 February 2022

CrossFit has gained recognition and interest among physically active populations being one of the most popular and rapidly growing exercise regimens worldwide. Due to the intense and repetitive nature of CrossFit, concerns have been raised over the p...

  • Article
  • Open Access
2 Citations
3,917 Views
35 Pages

Partitioning of Transportation Networks by Efficient Evolutionary Clustering and Density Peaks

  • Pamela Al Alam,
  • Joseph Constantin,
  • Ibtissam Constantin and
  • Clelia Lopez

24 February 2022

Road traffic congestion has became a major problem in most countries because it affects sustainable mobility. Partitioning a transport network into homogeneous areas can be very useful for monitoring traffic as congestion is spatially correlated in a...

  • Review
  • Open Access
39 Citations
10,578 Views
19 Pages

Machine Learning in Cereal Crops Disease Detection: A Review

  • Fraol Gelana Waldamichael,
  • Taye Girma Debelee,
  • Friedhelm Schwenker,
  • Yehualashet Megersa Ayano and
  • Samuel Rahimeto Kebede

24 February 2022

Cereals are an important and major source of the human diet. They constitute more than two-thirds of the world’s food source and cover more than 56% of the world’s cultivatable land. These important sources of food are affected by a varie...

  • Article
  • Open Access
37 Citations
6,935 Views
18 Pages

Machine Learning-Based Monitoring of DC-DC Converters in Photovoltaic Applications

  • Marco Bindi,
  • Fabio Corti,
  • Igor Aizenberg,
  • Francesco Grasso,
  • Gabriele Maria Lozito,
  • Antonio Luchetta,
  • Maria Cristina Piccirilli and
  • Alberto Reatti

23 February 2022

In this paper, a monitoring method for DC-DC converters in photovoltaic applications is presented. The primary goal is to prevent catastrophic failures by detecting malfunctioning conditions during the operation of the electrical system. The proposed...

  • Article
  • Open Access
4 Citations
4,046 Views
13 Pages

Reinforcement Learning for Mean-Field Game

  • Mridul Agarwal,
  • Vaneet Aggarwal,
  • Arnob Ghosh and
  • Nilay Tiwari

22 February 2022

Stochastic games provide a framework for interactions among multiple agents and enable a myriad of applications. In these games, agents decide on actions simultaneously. After taking an action, the state of every agent updates to the next state, and...

  • Article
  • Open Access
10 Citations
4,770 Views
15 Pages

22 February 2022

A domain that has gained popularity in the past few years is personalized advertisement. Researchers and developers collect user contextual attributes (e.g., location, time, history, etc.) and apply state-of-the-art algorithms to present relevant ads...

of 3

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
Algorithms - ISSN 1999-4893