• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1500-1506
• /
• 2020

In this paper, we study a scheduling problem based on reinforcement learning for overlay device-to-device (D2D) communication networks. Even though various technologies for D2D communication networks using Q-learning, which is one of reinforcement learning models, have been studied, Q-learning causes a tremendous complexity as the number of states and actions increases. In order to solve this problem, D2D communication technologies based on Deep Q Network (DQN) have been studied. In this paper, we thus design a DQN model by considering the characteristics of wireless communication systems, and propose a distributed scheduling scheme based on the DQN model that can reduce feedback and signaling overhead. The proposed model trains all parameters in a centralized manner, and transfers the final trained parameters to all mobiles. All mobiles individually determine their actions by using the transferred parameters. We analyze the performance of the proposed scheme by computer simulation and compare it with optimal scheme, opportunistic selection scheme and full transmission scheme.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1054-1061
• /
• 2003

Q-Learning, a representative algorithm of reinforcement learning, experiences repeatedly until estimation values about all state-action pairs of state space converge and achieve optimal policies. When the state space is high dimensional or continuous, complex reinforcement learning tasks involve very large state space and suffer from storing all individual state values in a single table. We introduce Q-Map that is new function approximation method to get classified policies. As an agent learns on-line, Q-Map groups states of similar situations and adapts to new experiences repeatedly. State-action pairs necessary for fine control are treated in the form of rule. As a result of experiment in maze environment and mountain car problem, we can achieve classified knowledge and extract easily rules from Q-Map

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.77-82
• /
• 2004

Reinforcement learning takes reward about selecting action when agent chooses some action and did state transition in Present state. this can be the important subject in reinforcement learning as temporal-credit assignment problems. In this paper, by new meta heuristic method to solve hard combinational optimization problem, examine Ant-Q learning method that is proposed to solve Traveling Salesman Problem (TSP) to approach that is based for population that use positive feedback as well as greedy search. And, suggest Ant-TD reinforcement learning method that apply state transition through diversification strategy to this method and TD-error. We can show through experiments that the reinforcement learning method proposed in this Paper can find out an optimal solution faster than other reinforcement learning method like ACS and Ant-Q learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.157-162
• /
• 2010

The cart-pole balancing problem is a pseudo-standard benchmark problem from the field of control methods including genetic algorithms, artificial neural networks, and reinforcement learning. In this paper, we propose a novel approach by using online reinforcement learning(OREL) to solve this cart-pole balancing problem. The objective is to analyze the learning method of the OREL learning system in the cart-pole balancing problem. Through experiment, we can see that approximate faster the optimal value-function than Q-learning.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.151-153
• /
• 2001

Q-Learning과 같은 기본적인 강화 학습 알고리즘은 문제의 사이즈가 커짐에 따라 성능이 크게 떨어지게 된다. 그 이유들로는 목표와의 거리가 멀어지게 되어 학습이 어려워지는 문제와 비 지향적 탐색을 사용함으로써 효율적인 탐색이 어려운 문제를 들 수 있다. 이들을 해결하기 위해 목표와의 거리를 줄일 수 있는 계층적 강화 학습 모델과 여러 가지 지향적 탐색 모델이 있어 왔다. 본 논문에서는 이들을 결합하여 계층적 강화 학습 모델에 지향적 탐색을 가능하게 하는 탐색 보너스를 도입한 강화 학습 모델을 제시한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.25-26
• /
• 2023

본 논문에서는 OpenAI Gym 환경에서 제공하는 CartPole-v1에 대해 강화학습을 통해 에이전트를 학습시키고, 학습에 적용되는 활성화함수의 성능을 비교분석하였다. 본 논문에서 적용한 활성화함수는 Sigmoid, ReLU, ReakyReLU 그리고 softplus 함수이며, 각 활성화함수를 DQN(Deep Q-Networks) 강화학습에 적용했을 때 보상 값을 비교하였다. 실험결과 ReLU 활성화함수를 적용하였을 때의 보상이 가장 높은 것을 알 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.1-5
• /
• 2005

The purpose of reinforcement learning is to maximize rewards from environment, and reinforcement learning agents learn by interacting with external environment through trial and error. Q-Learning, a representative reinforcement learning algorithm, is a type of TD-learning that exploits difference in suitability according to the change of time in learning. The method obtains the optimal policy through repeated experience of evaluation of all state-action pairs in the state space. This study chose n-Queen problem as an example, to which we apply reinforcement learning, and used Q-Learning as a problem solving algorithm. This study compared the proposed method using reinforcement learning with existing methods for solving n-Queen problem and found that the proposed method improves the convergence rate to the optimal solution by reducing the number of state transitions to reach the goal.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.862-872
• /
• 2014

The purpose of this study was to examine the affective outcome according to KCUE-Q1 in nursing students. The survey was performed with 424 nursing students of 3-year or 4-year that scheduled to graduate from college. Collected data was analyzed using descriptive statistics, t-test, one-way ANOVA and Pearson's correlation coefficient. The level of affective outcome was 2.69. The affective outcome was significantly different according to gender, grade, nursing education accreditation and club activity. Learning passion showed a positive correlation with learning experience and educational outcome. Learning experience showed a positive correlation with leaning passion and educational outcome. The findings of this study indicates a need to develop outcome-based nursing curriculum for nursing students. It is also necessary to evaluate affective outcome in undergraduate nursing students.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.329-338
• /
• 2013

Purpose: This study was to identify the types of subjectivity on PBL experience of freshmen in nursing students. Method: This study is exploratory research through Q methodology. From 102 Q populations, we selected 31 Q sorting was done by 25 of P sample. When the Q sorting is completed on nine point scale, we interviewed participants and documented their responses. The data was analyzed by using QUNAL program. Result: The result of the study showed 4 types. Four factors provided an explanation for 71.6% of total variances, and these four factors were analyzed and categorized as four types. We named type 1 as [positive pressure], type 2 as [relational friendly], type 3 as [creative benefit], type 4 as [paticipatory development]. Conclusion: In this study, PBL was valuable experience and recognized as a variety of perspectives for freshmen in nursing students. These findings indicate we suggest that planning of strategy for efficient operation on PBL was reflected above results.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.393-396
• /
• 2006

강화학습은 환경과 상호작용하는 과정을 통하여 목표를 이루기 위한 전략을 학습하는 방법으로써 에이전트의 학습방법으로 많이 사용한다. 독립적인 에이전트가 아닌 상호 의사소통이 가능한 다중 에이전트 환경에서 에이전트의 학습정보를 서로 검색 및 공유가 가능하다면 환경이 거대하더라도 기존의 강화학습 보다 빠르게 학습이 이루어질 것이다. 하지만 아직 다중 에이전트 환경에서 학습 방법에 대한 연구가 미흡하여 학습정보의 검색과 공유에 대해 다양한 방법들이 요구되고 있다. 본 논문에서는 대상 에이전트 학습 정보와 주변 에이전트들의 학습 정보 사이에 편집거리를 비교하여 유사한 에이전트를 찾고 그 에이전트 정보를 강화학습 사전정보로 사용함으로써 학습속도를 향상시킨 ED+Q-Learning 시스템을 제안한다.