The iterated prisoner's dilemma or IPD game has been widely used in modelling interactions among autonomous agents. According to the tournament competitions organized by Axelrod, Tit-for-Tat emerged as the most effective strategy on the assumption of an environment clinically free of communicative error or noiseless. However, with noise present, Tit-for- Tat contradictorily finds itself more difficult to maintain cooperation. In this study, the competitions of our proposed strategies and other Tit-for- Tat like strategies in the environment with different levels of noise are presented. The main result is that our proposed strategies provide the most effective performance in both round-robin tournaments and evolutionary dynamics.
{"title":"The Competitions of Forgiving Strategies in the Iterated Prisoner's Dilemma","authors":"Ruchdee Binmad, Mingchu Li, Nakema Deonauth, Theerawat Hungsapruek, Aree Limwudhikraijirath","doi":"10.1109/AGENTS.2018.8460036","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8460036","url":null,"abstract":"The iterated prisoner's dilemma or IPD game has been widely used in modelling interactions among autonomous agents. According to the tournament competitions organized by Axelrod, Tit-for-Tat emerged as the most effective strategy on the assumption of an environment clinically free of communicative error or noiseless. However, with noise present, Tit-for- Tat contradictorily finds itself more difficult to maintain cooperation. In this study, the competitions of our proposed strategies and other Tit-for- Tat like strategies in the environment with different levels of noise are presented. The main result is that our proposed strategies provide the most effective performance in both round-robin tournaments and evolutionary dynamics.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127158686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8460075
A. Ikenaga, S. Arai
It is crucial to know which criterion should be focused on, in a multi-objective decision making context, to select the best alternative from the multiple Pareto optimal solutions. However, in general, it is hard for the decision maker to express his/her own preference order for each criterion. In this study, we propose a preference elicitation method to estimate relative importance in terms of weights for each criterion by observing his/her processes of decision making. This method would make expert's preference elicited, and contribute at an important decision making point, such as urban planning,
{"title":"Inverse Reinforcement Learning Approach for Elicitation of Preferences in Multi-objective Sequential Optimization","authors":"A. Ikenaga, S. Arai","doi":"10.1109/AGENTS.2018.8460075","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8460075","url":null,"abstract":"It is crucial to know which criterion should be focused on, in a multi-objective decision making context, to select the best alternative from the multiple Pareto optimal solutions. However, in general, it is hard for the decision maker to express his/her own preference order for each criterion. In this study, we propose a preference elicitation method to estimate relative importance in terms of weights for each criterion by observing his/her processes of decision making. This method would make expert's preference elicited, and contribute at an important decision making point, such as urban planning,","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133228940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8458495
Tin Zar Wint Cho, May Thu Win, Aung Win
In this paper, the proposed system aims to enhance human action recognition by using skeletal features from Kinect sensor to obtain discriminative features. Joints distance feature is used for feature extraction. Instead of using traditional (non-static) K-means, such feature is clustered based on static K-means algorithm which takes statically the initial defined centroids at the first estimates for the K centroids and reduces the randomized starting centroids at all time to increase the accuracy of postures selection. Each posture is labelled by using artificial Neural Network (ANN) which makes the system more intelligent. Recognition of human action is performed using hidden Markov Model (HMM) based on the sequence of known poses to improve performance and accuracy. The proposed system recognizes the fundamental actions (walking, sitting, standing, and bending) and evaluated on the public dataset UTKinect-Action3D. The experimental results show the better accuracy rate on the static K-means than the non-static K-means.
{"title":"Human Action Recognition System based on Skeleton Data","authors":"Tin Zar Wint Cho, May Thu Win, Aung Win","doi":"10.1109/AGENTS.2018.8458495","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8458495","url":null,"abstract":"In this paper, the proposed system aims to enhance human action recognition by using skeletal features from Kinect sensor to obtain discriminative features. Joints distance feature is used for feature extraction. Instead of using traditional (non-static) K-means, such feature is clustered based on static K-means algorithm which takes statically the initial defined centroids at the first estimates for the K centroids and reduces the randomized starting centroids at all time to increase the accuracy of postures selection. Each posture is labelled by using artificial Neural Network (ANN) which makes the system more intelligent. Recognition of human action is performed using hidden Markov Model (HMM) based on the sequence of known poses to improve performance and accuracy. The proposed system recognizes the fundamental actions (walking, sitting, standing, and bending) and evaluated on the public dataset UTKinect-Action3D. The experimental results show the better accuracy rate on the static K-means than the non-static K-means.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127508506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8460052
Tatsuya Toyama, Takayuki Ito
Negotiation is one type of these possible interactions through which intelligent agents can resolve their conflicts and maximize their utility. Furthermore, automated negotiation approaches are expected to greatly reduce the efforts that stakeholders have to expend during real-life negotiations. In this regard, we conceal the preference information of negotiation participants to protect privacy in a real-world negotiation environment. However, in such a negotiation environment, it is difficult for negotiation participants to search effective agreement candidates as reaching agreements. Therefore, in this study, we propose a metric called the Metric of Opposition Level (MOL), which is used for analyzing negotiation scenarios in an environment in which participants' preferences are concealed. The proposed metric MOL quantitatively indicates the difficulty in reaching an agreement by measuring how hostile the opponent agent is. In particular, a third person can analyze negotiation scenarios in consideration of the difficulty in negotiation participants searching agreement candidates. Experimental results indicate the impact of the MOL on agent negotiation results and its vital role in building better negotiation strategies.
{"title":"Quantitatively Evaluating Difficulty in Reaching Agreements in Multilateral Closed Negotiation Scenarios","authors":"Tatsuya Toyama, Takayuki Ito","doi":"10.1109/AGENTS.2018.8460052","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8460052","url":null,"abstract":"Negotiation is one type of these possible interactions through which intelligent agents can resolve their conflicts and maximize their utility. Furthermore, automated negotiation approaches are expected to greatly reduce the efforts that stakeholders have to expend during real-life negotiations. In this regard, we conceal the preference information of negotiation participants to protect privacy in a real-world negotiation environment. However, in such a negotiation environment, it is difficult for negotiation participants to search effective agreement candidates as reaching agreements. Therefore, in this study, we propose a metric called the Metric of Opposition Level (MOL), which is used for analyzing negotiation scenarios in an environment in which participants' preferences are concealed. The proposed metric MOL quantitatively indicates the difficulty in reaching an agreement by measuring how hostile the opponent agent is. In particular, a third person can analyze negotiation scenarios in consideration of the difficulty in negotiation participants searching agreement candidates. Experimental results indicate the impact of the MOL on agent negotiation results and its vital role in building better negotiation strategies.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130105383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8460001
Ryo Funato, T. Sugawara
This paper proposes a method to efficiently allocate tasks to appropriate agents by forming teams based on the reciprocity in distributed environments where communication delay is not ignorable. Recent applications on a variety of devices such as PCs, tablets, and smartphones run in different locations to provide location-oriented and time-constrained services. These services are usually realized by agents on these devices communicating with single or multiple service agents operating on servers that are also deployed at multiple points. Because timely response is a key factor for quality of services, communication delay is significant in these applications. Thus, we propose a method in which agents allocate tasks in such a widely distributed environment to reduce the delay of response to the requested tasks by extending our previous work. Then, we experimentally show that our method could improve the overall performance by identifying which agents have high-throughput of task execution from the local viewpoint.
{"title":"Efficient Task Allocation with Communication Delay Based on Reciprocal Teams","authors":"Ryo Funato, T. Sugawara","doi":"10.1109/AGENTS.2018.8460001","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8460001","url":null,"abstract":"This paper proposes a method to efficiently allocate tasks to appropriate agents by forming teams based on the reciprocity in distributed environments where communication delay is not ignorable. Recent applications on a variety of devices such as PCs, tablets, and smartphones run in different locations to provide location-oriented and time-constrained services. These services are usually realized by agents on these devices communicating with single or multiple service agents operating on servers that are also deployed at multiple points. Because timely response is a key factor for quality of services, communication delay is significant in these applications. Thus, we propose a method in which agents allocate tasks in such a widely distributed environment to reduce the delay of response to the requested tasks by extending our previous work. Then, we experimentally show that our method could improve the overall performance by identifying which agents have high-throughput of task execution from the local viewpoint.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121412417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8459920
Yu-Ying Chen, Wei-Lun Chen, Szu-Hao Huang
Pairs trading is a statistical arbitrage strategy, which selects a set of assets with similar performance and produces profits during these asset prices far away from rational equilibrium. Once this phenomenon exists, traders can earn the spread by longing the underperforming asset and shorting the outperforming asset. This paper proposed a novel intelligent high-frequency pairs trading system in Taiwan Stock Index Futures (TX) and Mini Index Futures (MTX) market based on deep learning techniques. This research utilized the improved time series visualization method to transfer historical volatilities with different time frames into 2D images which are helpful in capturing arbitrage signals. Moreover, this research improved convolutional neural networks (CNN) model by combining the financial domain knowledge and filterbank mechanism. We proposed Filterbank CNN to extract high-quality features by replacing the random-generating filters with the arbitrage knowledge filters. In summary, the accuracy is enhanced through the proposed method, and it proves that the integrated information technology and financial knowledge could create the better pairs trading system.
{"title":"Developing Arbitrage Strategy in High-frequency Pairs Trading with Filterbank CNN Algorithm","authors":"Yu-Ying Chen, Wei-Lun Chen, Szu-Hao Huang","doi":"10.1109/AGENTS.2018.8459920","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8459920","url":null,"abstract":"Pairs trading is a statistical arbitrage strategy, which selects a set of assets with similar performance and produces profits during these asset prices far away from rational equilibrium. Once this phenomenon exists, traders can earn the spread by longing the underperforming asset and shorting the outperforming asset. This paper proposed a novel intelligent high-frequency pairs trading system in Taiwan Stock Index Futures (TX) and Mini Index Futures (MTX) market based on deep learning techniques. This research utilized the improved time series visualization method to transfer historical volatilities with different time frames into 2D images which are helpful in capturing arbitrage signals. Moreover, this research improved convolutional neural networks (CNN) model by combining the financial domain knowledge and filterbank mechanism. We proposed Filterbank CNN to extract high-quality features by replacing the random-generating filters with the arbitrage knowledge filters. In summary, the accuracy is enhanced through the proposed method, and it proves that the integrated information technology and financial knowledge could create the better pairs trading system.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121413347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/AGENTS.2018.8459963
Evan Dennison S. Livelo, C. Cheng
With dengue becoming a major concern in tropical countries such as the Philippines, it is important that public health officials are able to accurately determine the presence and magnitude of dengue activity as quickly as possible to facilitate fast emergency response. The prevalence of massive streams of publicly available data from social media make this possible through infoveillance. Infoveillance involves observing and analyzing online interactions to gather health-related data for informing decisions on public health. In this paper, we present a public health agent model that performs dengue infoveillance using a gated recurrent neural network classification model incorporated with pre-trained word embeddings and cross-label frequency calculation. We setup the agent to work on the Philippine Twitter stream as its primary environment. Further, we evaluate the agents classification ability using a holdout set of human-labeled tweets. Afterwards, we run a historical simulation where the trained agent works with a stream of six months worth of tweets from the Philippines and we correlate its infoveillance results with actual dengue morbidity data of that time period. Experiments show that the agent is capable of accurately identifying dengue-related tweets with low loss. Moreover, we confirm that the agent model can be used for determining actual dengue activity and can serve as an early warning system with high confidence.
{"title":"Intelligent Dengue Infoveillance Using Gated Recurrent Neural Learning and Cross-Label Frequencies","authors":"Evan Dennison S. Livelo, C. Cheng","doi":"10.1109/AGENTS.2018.8459963","DOIUrl":"https://doi.org/10.1109/AGENTS.2018.8459963","url":null,"abstract":"With dengue becoming a major concern in tropical countries such as the Philippines, it is important that public health officials are able to accurately determine the presence and magnitude of dengue activity as quickly as possible to facilitate fast emergency response. The prevalence of massive streams of publicly available data from social media make this possible through infoveillance. Infoveillance involves observing and analyzing online interactions to gather health-related data for informing decisions on public health. In this paper, we present a public health agent model that performs dengue infoveillance using a gated recurrent neural network classification model incorporated with pre-trained word embeddings and cross-label frequency calculation. We setup the agent to work on the Philippine Twitter stream as its primary environment. Further, we evaluate the agents classification ability using a holdout set of human-labeled tweets. Afterwards, we run a historical simulation where the trained agent works with a stream of six months worth of tweets from the Philippines and we correlate its infoveillance results with actual dengue morbidity data of that time period. Experiments show that the agent is capable of accurately identifying dengue-related tweets with low loss. Moreover, we confirm that the agent model can be used for determining actual dengue activity and can serve as an early warning system with high confidence.","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126738989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-07-01DOI: 10.1109/agents.2018.8460077
{"title":"Part VI: Social Networks and Social Learning","authors":"","doi":"10.1109/agents.2018.8460077","DOIUrl":"https://doi.org/10.1109/agents.2018.8460077","url":null,"abstract":"","PeriodicalId":248901,"journal":{"name":"2018 IEEE International Conference on Agents (ICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128446401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：