• 한국산업융합학회 논문집
• /
• 제25권4_2호
• /
• pp.645-653
• /
• 2022

Recently, deep reinforcement learning has been applied to a variety of industries, such as games, robotics, autonomous vehicles, and data cooling systems. An algorithm called reinforcement learning allows for automated asset allocation without the requirement for ongoing monitoring. It is free to choose its own policies. The purpose of this paper is to carry out an empirical analysis of the performance of asset allocation strategies. Among the strategies considered were the conventional Mean- Variance Optimization (MVO) and the Proximal Policy Optimization (PPO). According to the findings, the PPO outperformed both its benchmark index and the MVO. This paper demonstrates how dynamic asset allocation can benefit from the development of a reinforcement learning algorithm.

• 한국인터넷방송통신학회논문지
• /
• 제20권1호
• /
• pp.171-176
• /
• 2020

강화 학습은 인공지능 에이전트가 비디오 게임을 학습할 때 가장 효과적으로 사용되는 방법이다. 강화 학습을 위해 여지껏 많은 알고리즘들이 제시되어 왔지만 알고리즘마다 적용되는 분야에 따라 다른 성능을 보여주었다. 본 논문은 최근 강화 학습에서 주로 사용되는 알고리즘들의 성능이 2D 레이싱 게임에서 어떻게 달라지는지 비교 평가한다. 이를 위해 평가에서 사용할 성능 메트릭을 정의하고 각 알고리즘에 따른 메트릭의 값을 그래프로 비교하였다. 그 결과 ACER (Actor Critic with Experience Replay)를 사용할 경우 게임의 보상이 다른 알고리즘보다 평균적으로 높은 것을 알 수 있었고, 보상 값이 가장 낮은 알고리즘과의 차이는 157%였다.

• 한국가스학회지
• /
• 제27권2호
• /
• pp.49-56
• /
• 2023

4차 산업혁명으로 인공지능(AI, Artificial Intelligence) 관련 기술이 고도로 성장함에 따라 여러 분야에서 AI를 접목하는 사례가 증가하고 있다. 주요 원인은 정보통신기술이 발달됨에 따라 기하급수적으로 증가하는 데이터를 사람이 직접 처리·분석하는데 현실적인 한계가 있고, 새로운 기술을 적용하여 휴먼 에러에 대한 리스크도 감소시킬 수 있기 때문이다. 이번 연구에서는 '원격 전위 측정용터미널(T/B, Test Box)'로부터 수신된 데이터와 해당시점의 '원격 정류기' 출력을 수집 후, AI가 학습하도록 하였다. AI의 학습 데이터는 최초 수집된 데이터의 회기분석을 통한 데이터 전처리로 확보하였고, 학습모델은 심층 강화학습(DRL, Deep Reinforce-ment Learning) 알고리즘 중(中) Value기반의 Q-Learning모델이 적용하였다. 데이터 학습이 완료된 AI는 실제 도시가스 공급지역에 투입하여, 수신된 원격T/B 데이터를 기반으로 AI가 적절하게 대응하는지 검증하고, 이를 통해 향후 AI가 전기방식 관리에 적합한 수단으로 활용될 수 있는지 검증하고자 한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.9-11
• /
• 2022

Applying Reinforcement Learning in everyday applications and varied environments has proved the potential of the of the field and revealed pitfalls along the way. In robotics, a learning agent takes over gradually the control of a robot by abstracting the navigation model of the robot with its inputs and outputs, thus reducing the human intervention. The challenge for the agent is how to implement a feedback function that facilitates the learning process of an MDP problem in an environment while reducing the time of convergence for the method. In this paper we will implement a reward shaping system avoiding sparse rewards which gives fewer data for the learning agent in a ROS environment. Reward shaping prioritizes behaviours that brings the robot closer to the goal by giving intermediate rewards and helps the algorithm converge quickly. We will use a pseudocode implementation as an illustration of the method.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.226-234
• /
• 2024

The frequent handover problem and playing ping-pong effects in 5G (5th Generation) ultra-dense networking cannot be effectively resolved by the conventional handover decision methods, which rely on the handover thresholds and measurement reports. For instance, millimetre-wave LANs, broadband remote association techniques, and 5G/6G organizations are instances of group of people yet to come frameworks that request greater security, lower idleness, and dependable principles and correspondence limit. One of the critical parts of 5G and 6G innovation is believed to be successful blockage the board. With further developed help quality, it empowers administrator to run many systems administration recreations on a solitary association. To guarantee load adjusting, forestall network cut disappointment, and give substitute cuts in case of blockage or cut frustration, a modern pursuing choices framework to deal with showing up network information is require. Our goal is to balance the strain on BSs while optimizing the value of the information that is transferred from satellites to BSs. Nevertheless, due to their irregular flight characteristic, some satellites frequently cannot establish a connection with Base Stations (BSs), which further complicates the joint satellite-BS connection and channel allocation. SF redistribution techniques based on Deep Reinforcement Learning (DRL) have been devised, taking into account the randomness of the data received by the terminal. In order to predict the best capacity improvements in the wireless instruments of 5G and 6G IoT networks, a hybrid algorithm for deep learning is being used in this study. To control the level of congestion within a 5G/6G network, the suggested approach is put into effect to a training set. With 0.933 accuracy and 0.067 miss rate, the suggested method produced encouraging results.

• ETRI Journal
• /
• 제44권2호
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• 한국인터넷방송통신학회논문지
• /
• 제21권3호
• /
• pp.175-181
• /
• 2021

본 논문은 단기 에너지 사용량 예측을 위해 인공지능 기반의 접근법에 대해 분석한다. 본 논문에서는 단기 에너지 사용량 예측 기술에 자주 활용되는 지도학습 알고리즘의 한계를 개선하기 위해 강화학습 알고리즘을 활용한다. 지도학습 알고리즘 기반의 접근법은 충분한 성능을 위해 에너지 사용량 데이터뿐만 아니라 contextual information이 필요하여 높은 복잡성을 가진다. 데이터와 학습모델의 복잡성을 개선하기 위해 다중 에이전트 기반의 심층 강화학습 알고리즘을 제안하여 에너지 사용량 데이터로만 에너지 사용량을 예측한다. 공개된 에너지 사용량 데이터를 통해 시뮬레이션을 진행하여 제안한 에너지 사용량 예측 기법의 성능을 확인한다. 제안한 기법은 이상점의 특징을 가지는 데이터를 제외하고 실제값과 유사한 값을 예측하는 것을 보여준다.

• 한국인터넷방송통신학회논문지
• /
• 제23권4호
• /
• pp.9-15
• /
• 2023

기존의 단순 통계 기반 추천 시스템은 학생들의 수강 이력 데이터만을 활용하기 때문에 선호하는 수업을 찾는 것에 많은 어려움을 겪고 있다. 이를 해결하기 위해, 본 연구에서는 심층 강화학습 기반의 개인화된 전공과목 추천 시스템을 제안한다. 이 시스템은 학생의 학과, 학년, 수강 이력 등의 정형 데이터를 기반으로 학생들 간의 유사도를 측정하며, 이를 통해 각 전공과목에 대한 정보와 학생들의 강의 평가를 종합적으로 고려하여 가장 적합한 전공과목을 추천한다. 본 논문에서는 이 DRL 기반의 추천 시스템을 통해 대학생들이 전공과목을 선택하는 데에 유용한 정보를 제공하며, 이를 통계 기반 추천 시스템과 비교하였을 때 더 우수한 성능을 보여주는 것을 확인하였다. 시뮬레이션 결과, 심층 강화학습 기반의 추천 시스템은 통계 기반 추천 시스템에 비해 수강 과목 예측률에서 약 20%의 성능 향상을 보였다. 이러한 결과를 바탕으로, 학생들의 강의 평가를 반영하여 개인화된 과목 추천을 제공하는 새로운 시스템을 제안한다. 이 시스템은 학생들이 자신의 선호와 목표에 맞는 전공과목을 찾는 데에 큰 도움이 될 것으로 기대한다.

• 인터넷정보학회논문지
• /
• 제25권4호
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1150-1156
• /
• 2019

This paper explores a model-free value-based approach for solving survival gridworld problem. Survival gridworld problem opens up a challenge involving taking risks to gain better rewards. Classic value-based approach in model-free reinforcement learning assumes minimal risk decisions. The proposed method involves a hybrid on-policy and off-policy updates to experience roll-outs using a modified Q-based update equation that introduces a parametric linear rectifier and motivational discount. The significance of this approach is it allows model-free training of agents that take into account risk factors and motivated exploration to gain better path decisions. Experimentations suggest that the proposed method achieved better exploration and path selection resulting to higher episode scores than classic off-policy and on-policy Q-based updates.