• Broadcasting and Media Magazine
• /
• v.27 no.2
• /
• pp.26-34
• /
• 2022

강화 학습 기술은 많은 분야에서 매우 적극적으로 활용되는 기계 학습 기술 중의 하나이며 최근 이를 사용한 많은 연구 결과를 다양한 기관에서 활발하게 보여주고 있다. 본 고에서는 이러한 강화 학습 기술에 대한 기본적인 소개와 해당 기술의 심층 강화 학습으로의 발전에 대해서 논한다. 더불어 이러한 심층 강화 학습의 많은 분야 중에서 최근 활발히 논의되는 모방 학습에 대해서 알아보고 그 활용성에 대해서 논한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.75-76
• /
• 2022

현재 산업용 로봇 팔의 경로 계획을 생성할 때, 로봇 팔 경로 계획은 로봇 엔지니어가 수동으로 로봇을 제어하며 최적 경로 계획을 탐색한다. 미래에 고객의 다양한 요구에 따라 공정을 유연하게 변경하는 대량 맞춤 시대에는 기존의 경로 계획 수립 방식은 부적합하다. 심층강화학습 프레임워크는 가상 환경에서 로봇 팔 경로 계획 수립을 학습해 새로운 공정으로 변경될 때, 최적 경로 계획을 자동으로 수립해 로봇 팔에 전달하여 빠르고 유연한 공정 변경을 지원한다. 본 논문에서는 심층강화학습 에이전트를 위한 학습 환경 구축과 인공지능 모델과 학습 환경의 연동을 중심으로, 로봇 팔 경로 계획 수립을 위한 심층강화학습 프레임워크 구조를 설계한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.528-530
• /
• 2022

심층강화학습에 완전 연결 신경망과 합성곱 신경망은 잘 활용되는 것에 반해 순환 신경망은 잘 활용되지 않는다. 이는 강화학습이 마르코프 속성을 전제로 하기 때문이다. 지금까지의 강화학습은 환경이 마르코프 속성을 만족하도록 사전 작업이 필요했다, 본 논문에서는 마르코프 속성을 따르지 않는 환경에서 이러한 사전 작업 없이도 순환 신경망의 은닉 상태를 통해 마르코프 속성을 학습함으로써 학습 성능을 개선할 수 있다는 것을 소개한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.412-415
• /
• 2018

본 논문에서는 영상 기반 대화 연구를 위한 기존 GuessWhat?! 게임 환경의 한계성을 보완한 새로운 GuessWbat+ 게임 환경을 소개한다. 또 이 환경에서 동작하는 대화 에이전트를 위한 정책 기울기 기반의 심층 강화 학습 알고리즘인 MRRB의 설계와 구현에 대해서도 설명한다. 다양한 실험을 통해, 본 논문에서 제안한 GuessWbat+ 환경과 심층 강화 학습 알고리즘의 긍정적 효과를 입증해 보인다.

• 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.

• 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.

• 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.

• 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 IKEEE
• /
• v.23 no.4
• /
• pp.1381-1386
• /
• 2019

As traffic congestion in cities becomes more serious, intelligent traffic control is actively being researched. Reinforcement learning is the most actively used algorithm for traffic signal control, and recently Deep reinforcement learning has attracted attention of researchers. Extended versions of deep reinforcement learning have been emerged as deep reinforcement learning algorithm showed high performance in various fields. However, most of the existing traffic signal control were studied in a single intersection environment, and there is a limitation that the method at a single intersection does not consider the traffic conditions of the entire city. In this paper, we propose a cooperative traffic control at multi-intersection environment. The traffic signal control algorithm is based on a combination of extended versions of deep reinforcement learning and we considers traffic conditions of adjacent intersections. In the experiment, we compare the proposed algorithm with the existing deep reinforcement learning algorithm, and further demonstrate the high performance of our model with and without cooperative method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.215-219
• /
• 2021

In this paper, we propose a deep reinforcement learning algorithm-based bi-directional electricity negotiation scheme that adjusts and propose the price they want to exchange for negotiation over smart building and utility grid. By employing a deep Q network algorithm, which is a kind of deep reinforcement learning algorithm, the proposed scheme adjusts the price proposal of smart building and utility grid. From the simulation results, it can be verified that consensus on electricity price negotiation requires average of 43.78 negotiation process. The negotiation process under simulation settings and scenario can also be confirmed through the simulation results.