Deep Reinforcement Learning with Fully Convolutional Neural Network to Solve an Earthwork Scheduling Problem

Woo, Seongcheol; Yeon, Juneyeong; Ji, Mingi; Moon, Il‐Chul; Park, Jinkyoo

doi:10.1109/smc.2018.00717

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLP used in this work is a fully-connected layer which is deployed with fine regression. As a MLP is frequently used in reinforcement learning [26], [27], it is more likely to show feasible results when the curriculum settings from reinforcement learning are followed, where curriculum learning proceeds during all training epochs.…”

Section: Curriculum Learning For Multi-layer Perceptronmentioning

confidence: 99%

Curriculum Learning for Vehicle Lateral Stability Estimations

et al. 2021

View full text Add to dashboard Cite

Precise estimations of the roll and sideslip angles of autonomous vehicles are essential for autonomous driving, which requires further information about the vehicle state. As such, novel deep learning approaches have been introduced for this purpose. However, the majority of deep learning works focusing on vehicle dynamics estimations have yet to delve into learning strategies specifically for this task. Here, we argue that simply applying an adequate learning strategy to the task can boost the estimation performance. In this paper, we propose a simple yet effective curriculum learning strategy for better estimations of the roll and sideslip angles simultaneously. In addition, we compare our curriculum using a self-taught scoring function with a curriculum sorted by prior human knowledge, demonstrating its superiority. The proposed method outperforms the non-curriculum method by a large margin (up to a 16.5% decrease for sideslip as validation and 3.7% on a test), especially with regard to cornering (up to a 4% decrease). INDEX TERMSCurriculum learning, deep learning based estimator, roll angle, sensor fusion, sideslip angle, vehicle pose estimation.

show abstract

Section: Curriculum Learning For Multi-layer Perceptronmentioning

confidence: 99%

Curriculum Learning for Vehicle Lateral Stability Estimations

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In PixelRL approach, reinforcement learning (RL) is combined with state-of-theart image processing techniques like Convolutional Neural Networks (CNN) to solve real-time complex computer vision problems. Scheduling of important tasks or finding a shortest path between two points in images are few more examples where CNN extracts the features from images and RL learns the optimized way to proceed and perform scheduled task [337], [336] and [338].…”

Section: F Computer Visionmentioning

confidence: 99%

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Naeem

Rizvi

Coronato³

2020

IEEE Access

146

View full text Add to dashboard Cite

Due to the recent progress in Deep Neural Networks, Reinforcement Learning (RL) has become one of the most important and useful technology. It is a learning method where a software agent interacts with an unknown environment, selects actions, and progressively discovers the environment dynamics. RL has been effectively applied in many important areas of real life. This article intends to provide an in-depth introduction of the Markov Decision Process, RL and its algorithms. Moreover, we present a literature review of the application of RL to a variety of fields, including robotics and autonomous control, communication and networking, natural language processing, games and self-organized system, scheduling management and configuration of resources, and computer vision.

show abstract

“…The RL has been applied in many fields, such as in robotics, control, multiagent systems and optimization (Gambardella and Dorigo 2000;Kober et al 2013;Shao et al 2014;Bianchi et al 2015;Yliniemi and Tumer 2016;Da Silva et al 2019;Mnih et al 2015;Asiain et al 2019;Alipour et al 2018;Carvalho et al 2019;Li et al 2019;Low et al 2019;Bazzan 2019;Da Silva et al 2019). A growing interesting to apply the RL can be seen in combinatorial optimization (Gambardella and Dorigo 1995;Likas et al 1995;Miagkikh and Punch 1999;Mariano and Morales 2000;Sun et al 2001;Ma et al 2008;Liu and Zeng 2009;Lima Júnior et al 2010;Santos et al 2014;Alipour and Razavi 2015;Alipour et al 2018;Ottoni et al 2018;Woo et al 2018;Miki et al 2018;Chhabra and Warn 2019), such as the travelling salesman problem (TSP) (Gambardella and Dorigo 1995;Alipour et al 2018), Job-Shop Problem (Zhang and Dietterich 1995;Cunha et al 2020), the K-Server Problem (Costa et al 2016) and the multidimensional knapsack problem (MKP) (Arin and Rabadi 2017;Ottoni et al 2017). Although, it seems evident that a great number of works have been devoted to solving combinatorial optimization, less attention has been paid to the sequential ordering problem (SOP)…”

Section: Introductionmentioning

confidence: 99%

Tuning of reinforcement learning parameters applied to SOP using the Scott–Knott method

et al. 2019

View full text Add to dashboard Cite

In this paper, we present a technique to tune the reinforcement learning (RL) parameters applied to the sequential ordering problem (SOP) using the Scott-Knott method. The RL has been widely recognized as a powerful tool for combinatorial optimization problems, such as travelling salesman and multidimensional knapsack problems. It seems, however, that less attention has been paid to solve the SOP. Here, we have developed a RL structure to solve the SOP that can partially fill that gap. Two traditional RL algorithms, Q-learning and SARSA, have been employed. Three learning specifications have been adopted to analyze the performance of the RL: algorithm type, reinforcement learning function, and parameter. A complete factorial experiment and the Scott-Knott method are used to find the best combination of factor levels, when the source of variation is statistically different in analysis of variance. The performance of the proposed RL has been tested using benchmarks from the TSPLIB library. In general, the selected parameters indicate that SARSA overwhelms the performance of Q-learning.

show abstract

Deep Reinforcement Learning with Fully Convolutional Neural Network to Solve an Earthwork Scheduling Problem

Cited by 7 publications

References 19 publications

Curriculum Learning for Vehicle Lateral Stability Estimations

Curriculum Learning for Vehicle Lateral Stability Estimations

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Tuning of reinforcement learning parameters applied to SOP using the Scott–Knott method

Contact Info

Product

Resources

About