• 로봇학회논문지
• /
• 제17권1호
• /
• pp.40-47
• /
• 2022

A reward function suitable for a task is required to manipulate objects through reinforcement learning. However, it is difficult to design the reward function if the ample information of the objects cannot be obtained. In this study, a demonstration-based object manipulation algorithm called stochastic exploration guided by demonstration (SEGD) is proposed to solve the design problem of the reward function. SEGD is a reinforcement learning algorithm in which a sparse reward explorer (SRE) and an interpolated policy using demonstration (IPD) are added to soft actor-critic (SAC). SRE ensures the training of the critic of SAC by collecting prior data and IPD limits the exploration space by making SEGD's action similar to the expert's action. Through these two algorithms, the SEGD can learn only with the sparse reward of the task without designing the reward function. In order to verify the SEGD, experiments were conducted for three tasks. SEGD showed its effectiveness by showing success rates of more than 96.5% in these experiments.

• 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.

• Asia Marketing Journal
• /
• 제19권3호
• /
• pp.45-74
• /
• 2017

The current research proposes to fill a research gap by testing how reward uncertainty, different types of motivation, as well as individual risk-taking attitude affect consumers' promotion participation. Being offered with an uncertain reward, relative to individuals with extrinsic motivation, individuals with intrinsic motivation will have greater intention to participate in marketing promotion. In contrast, being offered with a certain reward, relative to individuals with intrinsic motivation, individuals with extrinsic motivation will have greater intention to participate in marketing promotion. This effect arises only among consumers having a low level of risk-taking attitude. For consumers having a high level of risk-taking attitude, their participation intention shows no significant difference between the two motivation type groups, under both certain and uncertain reward conditions. With an understanding of how consumer's response heterogeneously to promotions involving rewards, marketers can better understand not only how to use this promotional tactic more effectively, but also how to better allocate their budget for promotions.

• 대한전자공학회논문지TC
• /
• 제47권11호
• /
• pp.59-68
• /
• 2010

본 논문은 보상함수 수정을 통해 보다 완벽한 DSA(Dynamic Spectrum Access)를 수행하는 새로운 방법을 제시하였다. POMDP(Partially Observable Markov Decision Process)는 미래의 스펙트럼 상태를 예측하는데 사용되는 알고리즘으로서, 그 중 보상함수는 스펙트럼을 예측하는데 있어 가장 중요한 부분이다. 그러나 보상함수는 Busy 및 Idle의 두 가지 상태만 갖고 있기 때문에 채널에서 충돌이 발생하게 되면 보상함수는 Busy를 반환함으로써 2차 사용자의 성능을 감소시키게 된다. 따라서 본 논문에서는 기존의 Busy를 Busy 및 Collision 의 두 상태로 구분하였고, 이렇게 추가된 Collision 상태를 통해 2차 사용자의 채널 접근 기회를 보다 향상시킴으로서 데이터 전송율을 증대시킬 수 있도록 하였다. 또한 본 논문은 새로운 알고리즘의 신뢰도 벡터를 수학적으로 분석하였다. 마지막으로 시뮬레이션 결과를 통해 개선된 보상함수의 성능을 검증하고, 이를 통해 새로운 알고리즘이 CR 네트워크에서 2차 사용자의 성능을 향상시킬 수 있음을 보인다.

• 한국경영과학회지
• /
• 제38권1호
• /
• pp.103-121
• /
• 2013

Since American Airlines's mileage program emerged in market, loyalty programs have gained popularity. Many companies have generated many kinds of reward cards in order to induce precious consumers. As a result, reward cards are very important in consumer goods market and become diversified. In spite of its importance, little is known about how these cards influence consumer's perception. The prior research has not focused on reward card types and psychological variables. Accordingly this research intends to investigate psychological variables such as transaction coupling and sunk cost perception. According to the theory of regulatory focus, promotion focus consumers would point to gain-nongain frame work, but prevention focus consumers would point to loss-nonloss frame work. The paper proved the effect of reward card types and regulatory focus on transaction coupling and sunk cost perception. Based on the results from 2(type of card : visible vs invisible) ${\times}$ 2(regulatory focus: promotion vs prevention) between-subjects factorial design experiments, we found that consumer's transaction coupling and sunk cost perception of visible reward card are better recognized than invisible reward card. In addition, the results show that there is a significant interaction effect between the type of reward card and regulatory focus. Specifically promotion focused consumers tend to reveal better perception than prevention focused consumers in use of invisible cards. However, prevention focused consumers tend to show better perception than promotion focused consumers in use of visible cards. These findings will contribute to significant academic development and practically useful help to marketing managers.

• 대한가정학회지
• /
• 제38권8호
• /
• pp.29-51
• /
• 2000

The purpose of this study is to examine how midlife working women's psychological well-being is associated with their reward/cost of family role and work role according to their kinds of job. For empirical research, 627 married working women living in Seoul, aged between 40-55 answered the structured questionnaire. The subjects consisted of 301 professional working women and 326 non-professional working women. The data were analysed by the frequencies, mean, oneway ANOVA, and multiple regression. The major findings were as follows 1) Two sub areas of midlife working women's psychological well-being-self esteem and life satisfaction-were higher than an average level. 2) The more midlife working women performed family role and work role, they perceived reward more than cost. 3) For the professional working women, the more they perceived the reward of family role and work role, the higher their psychological well-being was. The more they perceived the cost of family role and work role, the lower their psychological well-being was. These consequencies applied to not only general reward/cost of family role and work role but also interrole reward/cost between family role and work role. For the non-professional working women, general and interrole reward of family role and work role had the positive effects on psychological well-being. Their general cost of spouse role, general and interrole cost of mother role, general cost of work role had the negative erects on psychological well-being. However interrole cost between spouse role and work role did not have a significant effect on psychological well-being. Finally, the result of multiple regression analysis showed that general reward of work role had the largest positive effect on midwife working women's self-esteem. General reward/cost of spouse role had the largest effect on their life satisfaction.

• 한국콘텐츠학회논문지
• /
• 제16권7호
• /
• pp.760-770
• /
• 2016

본 연구는 보상프로그램에 대한 가치가 보상프로그램에 대한 충성도에 미치는 영향과, 보상프로그램에 대한 충성도가 이를 운영하는 공연예술/전시장에 대한 충성도에 영향을 미치는지에 대한 충성도 전이 효과와 이들 충성도를 태도적 충성도와 행동적 충성도로 구분하여 충성도의 강화효과를 살펴보았다. 그 결과 보상프로그램에 대한 가치는 보상프로그램에 대한 충성도로 전이되는 것을 확인할 수 있었으며, 보상프로그램 내, 공연예술/전시장 내 태도적 충성도가 행동적 충성도에 영향을 미치는 충성도 강화 효과를 밝혔다. 또한 충성도 전이에 있어서 보상프로그램에 대한 행동적 충성도가 공연예술/전시장의 행동적 충성도에 긍정적인 영향을 미치는 반면, 태도적 충성도는 영향을 미치지 않는 것으로 나타나 충성도 전이효과는 부분적으로 살펴볼 수 있었다.

• 감성과학
• /
• 제20권4호
• /
• pp.113-126
• /
• 2017

The purpose of the study was to find grey matter (GM) and white matter (WM) volume reduction in the brain reward system among patients with alcohol dependency. This study investigated regional GM and WM in chronic alcoholic patients, focusing primarily on the reward system, including principal components of the mesocorticolimbic reward circuit as well as cortical areas with modulating and oversight functions. Sixteen abstinent long-term chronic alcoholic men and demographically matched 16 healthy control men participated in the study. Morphometric analysis was performed on magnetic resonance brain scans using voxel-based morphometry (VBM)-diffeomorphic Anatomical Registration through Exponentiated Liealgebra (DARTEL). We derived GM and WM volumes from total brain and cortical and subcortical reward-related structures. Morphometric analyses that revealed the total volume of GM and WM was reduced and cerebrospinal fluid (CSF) was increased in the alcohol group compared to control group. The pronounced volume reduction in the reward system was observed in the GM and WM of the nucleus accumbens (NAc), GM of the amygdala, GM and WM of the hippocampus, WM of the thalamus, GM and WM of the insula, GM of the dorsolateral prefrontal cortex (DLPFC), GM of the orbitofrontal cortex (OFC), GM of the cingulate cortex (CC), GM and WM of the parahippocampal gyrus in the alcohol group. We identified volume reductions in WM as well as GM of reward system in the patients with alcohol dependency. These structural deficits in the reward system elucidate underlying impairment in the emotional and cognitive processing in alcoholism.

• 간호행정학회지
• /
• 제15권3호
• /
• pp.434-443
• /
• 2009

Purpose: This study was performed to measure nurses' perception of reward, organizational commitment, turnover intention, and to examine the effect of the first two variables on turnover intention. Methods: This study was cross-sectional survey. Data were collected from 400 nurses working at 8 general hospitals in 6 cities from May 28 to July 18, 2008. Result: Nurses perceived that reward was 'important', and organizational commitment and turnover intention were 'middle'. Being under 30 years old the unmarried staff nurses' organizational commitment was significantly low in statistics and their turnover intention was high. The only financial reward had a positive relationship with turnover intention, and organizational commitment had a negative relationship. The influence variables on turnover intention were affective commitment, period of expected work, financial reward, age, normative commitment, and the explanation power of them was 57.2%. Conclusion: It is concluded that the manager working at a small-middle sized general hospitals in Korean provinces should develop and apply the strategies that can improve nurses' organizational commitment. And they also have to make their organizational reward system keep appropriately.

• 융합경영연구
• /
• 제7권1호
• /
• pp.15-25
• /
• 2019

Purpose - This paper attempts to derive effective performance-reward strategies for SMEs to raise the valence for their employees while using their relatively limited resources, which is one of the primary concerns raised by SME CEOs. Research design, data, and methodology - This paper draws on the four question items such as the financial/direct factors, the financial/indirect factors, the non-financial/direct factors and the non-financial/indirect performance-reward factors to shed light on the most important factors and aspects that need improving, using the AHP and IPA. Results - The overall findings on the SMEs' performance-reward factors of interest here are indicative of the need for rectifying their performance-reward systems. Conclusions - SMEs' performance-reward factors of interest here are indicative of the need for rectifying their performance-reward systems. In particular, despite the fact that SMEs can hardly offer high wages or bonuses as large enterprises do, the expectancy theory suggests it is better to reward employees as per a valid common system, while the equity theory underscores the need to maintain and reinforce the fairness in distribution, procedures and interactions.