• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.367-369
• /
• 2001

본 논문에서는 기존의 문어를 다루는 태거와는 달리 구어를 처리할 수 있는 구어태거를 구현하였다. 구어태거는 크게 심층구조와 표층구조의 두 가지 부분으로 구성되어 있으며, 촘스키의 구조에 따라 설계하였다. 심층구조에서 예측된 문장은 표층구조에서 실제의 입력과 음소열수준으로 비교되고 그 결과 가 다시 심층구조로 되메김된다. 이를 통해 가장 적합한 후부가 선택되며 또한 강화학습을 통해 문법과 어휘가 학습된다. 실험을 통해서 여러 가지 잡음이 섞인 입력단어를 본 태거가 얼마나 정확한 예측을 할 수 있는가를 보았으며, 그 결과 잡음에 강한 특성을 나타내는 것을 확인하였다.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.4
• /
• pp.1-8
• /
• 2020

Motion synthesis using physics-based controllers can generate a character animation that interacts naturally with the given environment and other characters. Recently, various methods using deep neural networks have improved the quality of motions generated by physics-based controllers. In this paper, we present a control policy learned by deep reinforcement learning (DRL) that enables Luxo, the mascot character of Pixar animation studio, to run towards a random goal location while imitating a reference motion and maintaining its balance. Instead of directly training our DRL network to make Luxo reach a goal location, we use a reference motion that is generated to keep Luxo animation's jumping style. The reference motion is generated by linearly interpolating predetermined poses, which are defined with Luxo character's each joint angle. By applying our method, we could confirm a better Luxo policy compared to the one without any reference motions.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.728-734
• /
• 2021

In recent years, there has been a strong interest in the end-to-end autonomous driving based on deep reinforcement learning. In this paper, we present a reward function of latent SAC deep reinforcement learning to improve the longitudinal driving performance of an agent vehicle. While the existing reward function significantly degrades the driving safety and efficiency, the proposed reward function is shown to maintain an appropriate headway distance while avoiding the front vehicle collision.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.102-105
• /
• 2019

본 논문에서는 심층 신경망 검색 방법을 사용하여 이미지 고해상도화를 위한 심층 신경망을 설계하는 방법을 구현하였다. 일반적으로 이미지 고해상도화, 잡음 제거 및 번짐 제거를 위한 심층신경망 구조는 사람이 설계하였다. 최근에는 이미지 분류 등 다른 영상처리 기법에서 사용하는 심층 신경망 구조를 검색하기 위한 방법이 연구되었다. 본 논문에서는 강화학습을 사용하여 이미지 고해상도화를 위한 심층 신경망 구조를 검색하는 방법을 제안하였다. 제안된 방법은 policy gradient 방법의 일종인 REINFORCE 알고리즘을 사용하여 심층 신경망 구조를 출력하여 주는 제어용 RNN(recurrent neural network)을 학습하고, 최종적으로 이미지 고해상도화를 잘 실현할 수 있는 심층 신경망 구조를 검색하여 설계하였다. 제안된 심층 신경망 구조를 사용하여 이미지 고해상도화를 구현하였고, 약 36.54dB 의 피크 신호 대비 잡음 비율(PSNR)을 가지는 것을 확인할 수 있었다.

• Electronics and Telecommunications Trends
• /
• v.34 no.6
• /
• pp.87-99
• /
• 2019

Reinforcement learning is a type of machine learning paradigm that forces agents to repeat the observation-action-reward process to assess and predict the values of possible future action sequences. This allows the agents to incrementally reinforce the desired behavior for a given observation. Thanks to the recent advancements of deep learning, reinforcement learning has evolved into deep reinforcement learning that introduces promising results in various control and optimization domains, such as games, robotics, autonomous vehicles, computing, industrial control, and so on. In addition to this trend, a number of programming libraries have been developed for importing deep reinforcement learning into a variety of applications. In this article, we briefly review and summarize 10 representative deep reinforcement learning libraries and compare them from a development project perspective.

• Journal of Internet of Things and Convergence
• /
• v.8 no.4
• /
• pp.1-7
• /
• 2022

As the number of IoT devices increases, power management of the cluster head, which acts as a gateway between the cluster and sink nodes in the IoT network, becomes crucial. Particularly when the cluster head is a mobile wireless terminal, the power consumption of the IoT network must be minimized over its lifetime. In addition, the delay of information transmission in the IoT network is one of the primary metrics for rapid information collecting in the IoT network. In this paper, we propose a low-power buffer management algorithm that takes into account the information transmission delay in an IoT network. By forwarding or skipping received packets utilizing deep Q learning employed in deep reinforcement learning methods, the suggested method is able to reduce power consumption while decreasing transmission delay level. The proposed approach is demonstrated to reduce power consumption and to improve delay relative to the existing buffer management technique used as a comparison in slotted ALOHA protocol.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.483-486
• /
• 2021

기존의 심층 강화학습은 상태, 행동, 정책 등을 모두 벡터 형태로 표현하는 강화학습으로서, 학습된 정책의 일반성과 해석 가능성에 제한이 있고 영역 지식을 학습에 효과적으로 활용하기도 어렵다는 한계성이 있다. 이러한 문제점들을 해결하기 위해 제안된 새로운 관계형 강화학습 프레임워크인 dNL-RRL은 상태, 행동, 그리고 학습된 정책을 모두 논리 서술자와 규칙들로 표현할 수 있다. 본 논문에서는 dNL-RRL을 기초로 공장 내 운송용 모바일 로봇의 제어를 위한 행동 정책 학습을 수행하였으며, 학습의 효율성 향상을 위해 인간 전문가의 사전 영역 지식을 활용하는 방안들을 제안한다. 다양한 실험들을 통해, 본 논문에서 제안하는 영역 지식을 활용한 관계형 강화학습 방법의 학습 성능 개선 효과를 입증한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1153-1160
• /
• 2021

This paper proposes a routing algorithm that determines the optimal path using deep reinforcement learning in software-defined networks. The deep reinforcement learning model for learning is based on DQN, the inputs are the current network state, source, and destination nodes, and the output returns a list of routes from source to destination. The routing task is defined as a discrete control problem, and the quality of service parameters for routing consider delay, bandwidth, and loss rate. The routing agent classifies the appropriate service class according to the user's quality of service profile, and converts the service class that can be provided for each link from the current network state collected from the SDN. Based on this converted information, it learns to select a route that satisfies the required service level from the source to the destination. The simulation results indicated that if the proposed algorithm proceeds with a certain episode, the correct path is selected and the learning is successfully performed.

• Journal of the Korean Society of Radiology
• /
• v.14 no.7
• /
• pp.991-1001
• /
• 2020

Supervised deep learning technologies for improving the image quality of computed tomography (CT) need a lot of training data. When input images have different characteristics with training images, the technologies cause structural distortion in output images. In this study, an imaging model based on the deep reinforcement learning (DRL) was developed for overcoming the drawbacks of the supervised deep learning technologies and reducing noise in CT images. The DRL model was consisted of shared, value and policy networks, and the networks included convolutional layers, rectified linear unit (ReLU), dilation factors and gate rotation unit (GRU) in order to extract noise features from CT images and improve the performance of the DRL model. Also, the quality of the CT images obtained by using the DRL model was compared to that obtained by using the supervised deep learning model. The results showed that the image accuracy for the DRL model was higher than that for the supervised deep learning model, and the image noise for the DRL model was smaller than that for the supervised deep learning model. Also, the DRL model reduced the noise of the CT images, which had different characteristics with training images. Therefore, the DRL model is able to reduce image noise as well as maintain the structural information of CT images.