• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.166-175
• /
• 2023

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Q-learning.

• 한국정보처리학회논문지
• /
• 제6권5호
• /
• pp.1303-1311
• /
• 1999

In order to learn in dynamic environments, reinforcement learning algorithms like Q-learning, TD(0)-learning, TD(λ)-learning have been proposed. however, most of them have a drawback of very slow learning because the reinforcement value is given when they reach their goal state. In this thesis, we have proposed a reinforcement learning method that can approximate fast to the goal state in maze environments. The proposed reinforcement learning method is separated into global learning and local learning, and then it executes learning. Global learning is a learning that uses the replacing eligibility trace method to search the goal state. In local learning, it propagates the goal state value that has been searched through global learning to neighboring sates, and then searches goal state in neighboring states. we can show through experiments that the reinforcement learning method proposed in this thesis can find out an optimal solution faster than other reinforcement learning methods like Q-learning, TD(o)learning and TD(λ)-learning.

• 정보처리학회논문지B
• /
• 제9B권2호
• /
• pp.155-162
• /
• 2002

강화 학습(reinforcement teaming)은 시행-착오(trial-and-er개r)를 통해 동적 환경과 상호작용하면서 학습을 수행하는 학습 방법으로, 실시간 강화 학습(online reinforcement learning)과 지연 강화 학습(delayed reinforcement teaming)으로 분류된다. 본 논문에서는 미로 환경에서 최단 경로를 빠르게 탐색할 수 있는 실시간 강화 학습 시스템(ONRELS : Outline REinforcement Learning System)을 제안한다. ONRELS는 현재 상태에서 상태전이를 하기 전에 선택 가능한 모든 (상태-행동) 쌍에 대한 평가 값을 갱신하고 나서 상태전이를 한다. ONRELS는 미로 환경의 상태 공간을 압축(compression)하고 나서 압축된 환경과 시행-착오를 통해 상호 작용하면서 학습을 수행한다. 실험을 통해 미로 환경에서 ONRELS는 TD -오류를 이용한 Q-학습과 $TD(\lambda{)}$를 이용한 $Q(\lambda{)}$-학습보다 최단 경로를 빠르게 탐색할 수 있음을 알 수 있었다.

• 한국정보처리학회논문지
• /
• 제6권3호
• /
• pp.633-640
• /
• 1999

Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like Q-learning and TD(Temporal Difference)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present COMREL(COMpressed REinforcement Learning) algorithm for finding the shortest path fast in a maze environment, select the candidate states that can guide the shortest path in compressed maze environment, and learn only the candidate states to find the shortest path. After comparing COMREL algorithm with the already existing Q-learning and Priortized Sweeping algorithm, we could see that the learning time shortened very much.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.420-426
• /
• 1998

Evolutionary algorithms are probabilistic optimization algorithms based on the model of natural evolution. Recently the efforts to improve the performance of evolutionary algorithms have been made extensively. In this paper, we introduce the research for improving the convergence rate and search faculty of evolution algorithms by using reinforcement learning. After providing an introduction to evolution algorithms and reinforcement learning, we present adaptive genetic algorithms, reinforcement genetic programming, and reinforcement evolution strategies which are combined with reinforcement learning. Adaptive genetic algorithms generate mutation probabilities of each locus by interacting with the environment according to reinforcement learning. Reinforcement genetic programming executes crossover and mutation operations based on reinforcement and inhibition mechanism of reinforcement learning. Reinforcement evolution strategies use the variances of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length.

• 한국인터넷방송통신학회논문지
• /
• 제10권5호
• /
• pp.265-270
• /
• 2010

강화학습(reinforcement learning)은 동적 환경과 시행-착오를 통해 상호 작용하면서 학습을 수행한다. 그러므로 동적 환경에서 TD-학습과 TD(${\lambda}$)-학습과 같은 강화학습 방법들은 전통적인 통계적 학습 방법보다 더 빠르게 학습을 할 수 있다. 그러나 제안된 대부분의 강화학습 알고리즘들은 학습을 수행하는 에이전트(agent)가 목표 상태에 도달하였을 때만 강화 값(reinforcement value)이 주어지기 때문에 최적 해에 매우 늦게 수렴한다. 본 논문에서는 미로 환경(maze environment)에서 최단 경로를 빠르게 찾을 수 있는 강화학습 방법(GORLS : Goal-Directed Reinforcement Learning System)을 제안하였다. GDRLS 미로 환경에서 최단 경로가 될 수 있는 후보 상태들을 선택한다. 그리고 나서 최단 경로를 탐색하기 위해 후보 상태들을 학습한다. 실험을 통해, GDRLS는 미로 환경에서 TD-학습과 TD(${\lambda}$)-학습보다 더 빠르게 최단 경로를 탐색할 수 있음을 알 수 있다.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권11호
• /
• pp.1431-1438
• /
• 2004

강화학습(reinforcement learning)은 온라인으로 환경(environment)과 상호작용 하는 과정을 통하여 목표를 이루기 위한 전략을 학습한다. 강화학습의 기본적인 알고리즘인 Q-learning의 학습 속도를 가속하기 위해서, 거대한 상태공간 문제(curse of dimensionality)를 해결할 수 있고 강화학습의 특성에 적합한 함수 근사 방법이 필요하다. 본 논문에서는 이러한 문제점들을 개선하기 위해서, 온라인 퍼지 클러스터링(online fuzzy clustering)을 기반으로 한 Fuzzy Q-Map을 제안한다. Fuzzy Q-Map은 온라인 학습이 가능하고 환경의 불확실성을 표현할 수 있는 강화학습에 적합한 함수근사방법이다. Fuzzy Q-Map을 마운틴 카 문제에 적용하여 보았고, 학습 초기에 학습 속도가 가속됨을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.149.5-149
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent´s dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless ...

• Computers and Concrete
• /
• 제29권3호
• /
• pp.145-159
• /
• 2022

In this study, the extreme learning machine and deep learning models were devised to estimate the bond strength of corroded reinforcement in concrete. The six inputs and one output were used in this study. The compressive strength, concrete cover, bond length, steel type, diameter of steel bar, and corrosion level were selected as the input variables. The results of bond strength were used as the output variable. Moreover, the Analysis of variance (Anova) was used to find the effect of input variables on the bond strength of corroded reinforcement in concrete. The prediction results were compared to the experimental results and each other. The extreme learning machine and the deep learning models estimated the bond strength by 99.81% and 99.99% accuracy, respectively. This study found that the deep learning model can be estimated the bond strength of corroded reinforcement with higher accuracy than the extreme learning machine model. The Anova results found that the corrosion level was found to be the input variable that most affects the bond strength of corroded reinforcement in concrete.