• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.217-220
• /
• 2005

The RPO algorithm is a recently developed tool in the area of reinforcement Loaming, And it has been shown In be very successful in several application problems. In this paper, we consider a robot-control problem utilizing a modified RPO algorithm in which its critic network is adapted via RLS(Recursive Least Square) algorithm. We also developed a MATLAB-based animation program, by which the effectiveness of the training algorithms were observed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.60-66
• /
• 1997

This paper presents a fuzzy inference-based reinforcement learning algorithm of dynamci recurrent neural networks, which is very similar to the psychological learning method of higher animals. By useing the fuzzy inference technique the linguistic and concetional expressions have an effect on the controller's action indirectly, which is shown in human's behavior. The intervlas of fuzzy membership functions are found optimally by genetic algorithms. And using recurrent neural networks composed of dynamic neurons as action-generation networks, past state as well as current state is considered to make an action in dynamical environment. We show the validity of the proposed learning algorithm by applying it to the inverted pendulum control problem.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.297-305
• /
• 2021

Large amount of data is being generated in gaming servers due to the increase in the number of users and the variety of game services being provided. In particular, load balancing schemes for gaming servers are crucial consideration. The existing literature proposes algorithms that distribute loads in servers by mostly concentrating on load balancing and cooperative offloading. However, many proposed schemes impose heavy restrictions and assumptions, and such a limited service classification method is not enough to satisfy the wide range of service requirements. We propose a load balancing agent that combines the dynamic allocation programming method, a type of greedy algorithm, and proximal policy optimization, a reinforcement learning. Also, we compare performances of our proposed scheme and those of a scheme from previous literature, ProGreGA, by running a simulation.

• Electronics and Telecommunications Trends
• /
• v.38 no.4
• /
• pp.95-103
• /
• 2023

The importance of the decentralized training with decentralized execution (DTDE) framework is well-known in the study of multiagent reinforcement learning. In many real-world environments, agents cannot share information. Hence, they must be trained in a decentralized manner. However, the DTDE framework has been less studied than the centralized training with decentralized execution framework. One of the main reasons is that many problems arise when training agents in a decentralized manner. For example, DTDE algorithms are often computationally demanding or can encounter problems with non-stationarity. Another reason is the lack of simulation environments that can properly handle the DTDE framework. We discuss current research trends in the DTDE framework.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.406-409
• /
• 2023

With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.205-211
• /
• 2024

Effective warehouse management requires advanced resource planning to optimize profits and space. Robots offer a promising solution, but their effectiveness relies on embedded artificial intelligence. Multi-agent reinforcement learning (MARL) enhances robot intelligence in these environments. This study explores various MARL algorithms using the Multi-Robot Warehouse Environment (RWARE) to determine their suitability for warehouse resource planning. Our findings show that cooperative MARL is essential for effective warehouse management. IA2C outperforms MAA2C and VDA2C on smaller maps, while VDA2C excels on larger maps. IA2C's decentralized approach, focusing on cooperation over collaboration, allows for higher reward collection in smaller environments. However, as map size increases, reward collection decreases due to the need for extensive exploration. This study highlights the importance of selecting the appropriate MARL algorithm based on the specific warehouse environment's requirements and scale.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.489-489
• /
• 2000

Recently, Reinforcement Learning(RL) methods have been used far teaming problems in Partially Observable Markov Decision Process(POMDP) environments. Conventional RL-methods, however, have limited applicability to POMDP To overcome the partial observability, several algorithms were proposed [5], [7]. The aim of this paper is to extend our previous algorithm for POMDP, called Labeling Q-learning(LQ-learning), which reinforces incomplete information of perception with labeling. Namely, in the LQ-learning, the agent percepts the current states by pair of observation and its label, and the agent can distinguish states, which look as same, more exactly. Labeling is carried out by a hash-like function, which we call Labeling Function(LF). Numerous labeling functions can be considered, but in this paper, we will introduce several labeling functions based on only 2 or 3 immediate past sequential observations. We introduce the basic idea of LQ-learning briefly, apply it to maze problems, simple POMDP environments, and show its availability with empirical results, look better than conventional RL algorithms.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.724-729
• /
• 2001

This paper discusses the composition of the theory of reinforcement learning, which is applied in real-time learning, and evolutionary strategy, which proves its the superiority in the finding of the optimal solution at the off-line learning method. The individuals are reduced in order to learn the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because the learning process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against the outside disturbances.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• Geomechanics and Engineering
• /
• v.38 no.3
• /
• pp.231-247
• /
• 2024

The use of lime stabilization and geosynthetic reinforcement is a common approach to improve the performance of fine-grained soils in geotechnical applications. However, the impact of this combination on the soil-geosynthetic interaction remains unclear. This study addresses this gap by evaluating the interface efficiency and soil-geosynthetic interaction parameters of lime-stabilized clay (2%, 4%, 6%, and 8% lime content) reinforced with geotextile or geogrid using direct shear tests at various curing times (1, 7, 14, and 28 days). Additionally, machine learning algorithms (Support Vector Machine and Artificial Neural Network) were employed to predict soil shear strength. Findings revealed that lime stabilization significantly increased soil shear strength and interaction parameters, particularly at the optimal lime content (4%). Notably, stabilization improved the performance of soil-geogrid interfaces but had an adverse effect on soil-geotextile interfaces. Furthermore, machine learning algorithms effectively predicted soil shear strength, with sensitivity analysis highlighting lime percentage and geosynthetic type as the most significant influencing factors.