• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.23-29
• /
• 2023

In this paper, we introduce a method to obtain high-quality results at a low cost for simulating musculoskeletal characters based on data from the reference motion through motion capture on two-legged walking through reinforcement learning. We reset the motion data of the reference motion to allow the character model to perform, and then train the corresponding motion to be learned through reinforcement learning. We combine motion imitation of the reference model with minimal metabolic energy for the muscles to learn to allow the musculoskeletal model to perform two-legged walking in the desired direction. In this way, the musculoskeletal model can learn at a lower cost than conventional manually designed controllers and perform high-quality bipedal walking.

• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.179-188
• /
• 2008

An important issue in multiagent reinforcement learning is how an agent should team its optimal policy through trial-and-error interactions in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for multiagent reinforcement teaming tend to apply single-agent reinforcement learning techniques without any extensions or are based upon some unrealistic assumptions even though they build and use explicit models of other agents. In this paper, basic concepts that constitute the common foundation of multiagent reinforcement learning techniques are first formulated, and then, based on these concepts, previous works are compared in terms of characteristics and limitations. After that, a policy model of the opponent agent and a new multiagent reinforcement learning method using this model are introduced. Unlike previous works, the proposed multiagent reinforcement learning method utilize a policy model instead of the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper. the Cat and Mouse game is introduced as an adversarial multiagent environment. And effectiveness of the proposed multiagent reinforcement learning method is analyzed through experiments using this game as testbed.

• Structural Engineering and Mechanics
• /
• v.18 no.5
• /
• pp.541-563
• /
• 2004

For reaching large inelastic deformations without a substantial loss in strength, the potential plastic hinge regions of the reinforced concrete structural members should be confined by adequate transverse reinforcement. Therefore, simple and realistic representation of confined concrete behaviour is needed for inelastic analysis of reinforced concrete structures. In this study, a trilinear stress-strain model is proposed for the axial behaviour of confined concrete. The model is based on experimental work that was carried out on nearly full size specimens. During the interpretation of experimental data, the buckling and strain hardening of the longitudinal reinforcement are also taken into account. The proposed model is used for predicting the stress-strain relationships of confined concrete specimens tested by other researchers. Although the proposed model is simpler than most of the available models, the comparisons between the predicted results and experimental data indicate that it can represent the stress-strain relationship of confined concrete quite realistically.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2942-2960
• /
• 2022

The core of cognitive radio is the problem concerning intelligent decision-making for communication parameters, the objective of which is to find the most appropriate parameter configuration to optimize transmission performance. The current algorithms have the disadvantages of high dependence on prior knowledge, large amount of calculation, and high complexity. We propose a new decision-making model by making full use of the interactivity of reinforcement learning (RL) and applying the Q-learning algorithm. By simplifying the decision-making process, we avoid large-scale RL, reduce complexity and improve timeliness. The proposed model is able to find the optimal waveform parameter configuration for the communication system in complex channels without prior knowledge. Moreover, this model is more flexible than previous decision-making models. The simulation results demonstrate the effectiveness of our model. The model not only exhibits better decision-making performance in the AWGN channels than the traditional method, but also make reasonable decisions in the fading channels.

• Journal of Forest and Environmental Science
• /
• v.30 no.1
• /
• pp.113-119
• /
• 2014

To examine the soil reinforcement by the shrub with shallow root systems for slope stability, we developed insitu apparatus for direct shear test and conducted the insitu field tests for Lespedeza cyrtobotrya, a representative revegetation species for artificial hillslopes. The insitu field tests were conducted for two different soil conditions (the rooted soils and non-rooted soils) and we then compared the experimental values with those calculated from the Wu model. The results showed that the soil reinforcement derived from the insitu field tests ranged from 0.01525 to 0.1438 $kgf/cm^2$ while the one calculated from the Wu model ranged from 0.1952 to 0.2696 $kgf/cm^2$. Our finding suggests more field tests are needed to collect the related parameters in the model application thereby predicting the reliable soil reinforcement by the shrub root systems.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.41-48
• /
• 2021

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.11a
• /
• pp.1109-1114
• /
• 2001

This paper describes an attempt to develop a new truss model for reinforced concrete beams failing in shear based on a rational behavioral model. The key idea incorporated with truss model is the internal force state factor which is able to express global state of internal force flow in cracked reinforced concrete beams subjected to shear and bending. A new truss model using internal force state factor may provide a comprehensive result of shear strength in reinforced concrete beams without web reinforcement.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.19 no.3
• /
• pp.109-120
• /
• 2015

The purpose of this study was to investigate the performance of new hollow reinforced concrete (RC) bridge pier sections with triangular reinforcement details. The proposed triangular reinforcement details are economically feasible and rational and facilitate shorter construction periods. A model of pier sections with triangular reinforcement details was tested under quasi-static monotonic loading. As a result, proposed triangular reinforcement details was equal to existing reinforcement details in terms of required performance. In the companion paper, the parametric study for the performance assessment of new hollow RC bridge pier sections with triangular reinforcement details is performed.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.17 no.3
• /
• pp.107-115
• /
• 2013

The purpose of this study was to investigate the performance of hollow reinforced concrete bridge column sections with reinforcement details for material quantity reduction. The proposed reinforcement details has have economic feasibility and rationality and makes construction periods shorter. A model of column sections with reinforcement details for material quantity reduction was tested under quasistatic monotonic loading. As a result, the proposed reinforcement details for material quantity reduction was were equal to existing reinforcement details in terms of the required performance. In the a subsequent paper, the an experimental and analytical study will be performed for the performance assessment of hollow reinforced concrete bridge column sections with reinforcement details for material quantity reduction will be performed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.495-512
• /
• 2022

Due to the concentration of population in the city center, the aboveground structures are saturated, and the development of underground structures becomes important. In addition, it is necessary to apply the reinforcement construction method for the pillar part of the adjacent tunnel that can secure stability, economy, and workability to the site. In this study, the tunnel pillar reinforcement method using prestress and grouting was reviewed. There are various reinforcement methods that can compensate for the problems of the side tunnel, but as the tunnel pillar construction method using prestress and grouting is judged to be excellent in field applicability, stability, and economic feasibility, it is necessary to review the theoretical and numerical analysis of the actual behavior mechanism. Therefore, a scaled-down model experiment was conducted. The reduced model experiment was divided into PC stranded wire + steel pipe reinforcement grouting + prestress (Case 1), PC strand + steel pipe reinforcement grouting (Case 2), and no reinforcement (Case 3), and the displacement of the pillar and the earth pressure applied to the wall were measured. Through experiments, it was confirmed that the PC stranded wire + steel pipe reinforcement grouting + prestress method is the most excellent reinforcement method among various construction methods. It was judged that it could be derived.