发布求助
文献互助 智能选刊 最新文献

2019 IEEE International Conference on Agents (ICA)最新文献

筛选
英文 中文
End-to-end Deep Reinforcement Learning for Multi-agent Collaborative Exploration 面向多智能体协同探索的端到端深度强化学习
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929192
Zichen Chen, Budhitama Subagdja, A. Tan
{"title":"End-to-end Deep Reinforcement Learning for Multi-agent Collaborative Exploration","authors":"Zichen Chen, Budhitama Subagdja, A. Tan","doi":"10.1109/AGENTS.2019.8929192","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929192","url":null,"abstract":"Exploring an unknown environment by multiple autonomous robots is a major challenge in robotics domains. As multiple robots are assigned to explore different locations, they may interfere each other making the overall tasks less efficient. In this paper, we present a new model called CNN-based Multi-agent Proximal Policy Optimization (CMAPPO) to multi-agent exploration wherein the agents learn the effective strategy to allocate and explore the environment using a new deep reinforcement learning architecture. The model combines convolutional neural network to process multi-channel visual inputs, curriculum-based learning, and PPO algorithm for motivation based reinforcement learning. Evaluations show that the proposed method can learn more efficient strategy for multiple agents to explore the environment than the conventional frontier-based method.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122619050","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}
引用次数: 15
An Analysis of Threads with No Responses in Online Asynchronous Discussions 在线异步讨论中无响应线程的分析
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929144
T. Nakazawa, Tomoyuki Tatsumi
{"title":"An Analysis of Threads with No Responses in Online Asynchronous Discussions","authors":"T. Nakazawa, Tomoyuki Tatsumi","doi":"10.1109/AGENTS.2019.8929144","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929144","url":null,"abstract":"This study examines the causes of “no-response threads” in thread-based online discussion support systems. We investigated the factors contributing to the occurrence of no-response threads by using a logistic regression analysis of discussions on the topic of Nagoya City’s attractions in the online discussion system COLLAGREE. Results showed that the content quality of a post did not significantly affect the occurrence of no-response threads in the divergence phase, where non-response was found to be more dependent on environmental factors such as the displayed time on the first page and the number of entries and unique viewers after the thread was posted. On the other hand, in the convergence phase, content quality greatly affected whether a new post would receive a response.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133640611","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}
引用次数: 2
Modeling multi-objectivization mechanism in multi-agent domain 多智能体领域多目标机制建模
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929171
Kousuke Nishi, S. Arai
{"title":"Modeling multi-objectivization mechanism in multi-agent domain","authors":"Kousuke Nishi, S. Arai","doi":"10.1109/AGENTS.2019.8929171","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929171","url":null,"abstract":"Many real-world tasks require making sequential decisions that involve multiple conflicting objectives. Furthermore, there exist multiple decision-makers, called multiagent, each of whom pursues its own profit. Thus, each agent should take into account the effect of other agents ‘ decisions to reach a point of compromise. For example, each agent decides with thought of other agents ‘ behavior in the decision of selecting the faster driving route to the destination, selecting a supermarket checkout line, and so on. For solving a sequential multi-objective decision problem, a multi-objective reinforcement learning (MORL) approach has been investigated.However, current research on MORL cannot deal with the multi-agent system where existing agents are influenced one another. Therefore, in this study, we expand the conventional multi-objective reinforcement learning by introducing the idea of multi-objectivization with dynamic weight setting of other decision-makers. In an experiment, our proposed model with dynamic weight can express the cooperative behaviors that seems to be considered other decision-makers in the multiagent environment.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125073019","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}
引用次数: 0
Deep Learning in Model Risk Neutral Distribution for Option Pricing 期权定价模型风险中性分布的深度学习
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929176
Chin-chiang Chou, Jhih-Chen Liu, Chiao-Ting Chen, Szu-Hao Huang
{"title":"Deep Learning in Model Risk Neutral Distribution for Option Pricing","authors":"Chin-chiang Chou, Jhih-Chen Liu, Chiao-Ting Chen, Szu-Hao Huang","doi":"10.1109/AGENTS.2019.8929176","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929176","url":null,"abstract":"Option pricing has been studied extensively in recent years. An important issue in option pricing is the estimation of the risk neutral distribution of an underlying asset. Better estimation of this distribution can lead to a more rational investment, enabling one to earn an equal return with lower risk. To price options precisely and correctly, traditional financial engineering methods make some assumptions for the risk neutral distribution. However, some assumptions of traditional methods have proved inappropriate and insufficient in empirical option pricing analysis. To address these problems in option pricing, this study adopts a data-driven approach. Owing to advances in hardware and software, studies have been using deep learning methods to price options; however, these have not adequately considered the risk neutral distribution. This may cause an uncontrollable risk, thereby preventing the real-world application of the model. To overcome these problems, this study proposes a deep learning method with a mixture distribution model. Further, it generates a rational risk neutral distribution with accurate empirical pricing analysis.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129922998","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}
引用次数: 0
Running Reinforcement Learning Agents on GPU for Many Simulations of Two-Person Simultaneous Games 在GPU上运行强化学习代理进行多人同时博弈仿真
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929206
Koichi Moriyama, Yoshiya Kurogi, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka
{"title":"Running Reinforcement Learning Agents on GPU for Many Simulations of Two-Person Simultaneous Games","authors":"Koichi Moriyama, Yoshiya Kurogi, Atsuko Mutoh, Tohgoroh Matsui, Nobuhiro Inuzuka","doi":"10.1109/AGENTS.2019.8929206","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929206","url":null,"abstract":"It is desirable for multi-agent simulation to be run in parallel; if many agents run simultaneously, the total run time is reduced. It is popular to use GPGPU technology as an inexpensive parallelizing approach in simulation, but the “agents” runnable on GPU were simple, rule-based ones like elements in a scientific simulation. This work implements more complicated, learning agents on GPU. We consider an environment where many reinforcement learning agents learning their behavior in an iterated two-person simultaneous game while changing peers. It is necessary to run many simulations in each of which a pair of agents play the game. In this work, we implement on GPU the simulations where the agents learn with reinforcement learning and compare two methods assigning the simulations to GPU cores.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126216783","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}
引用次数: 0
Maximizing Social Welfare in Fractional Hedonic Games using Shapley Value 分数享乐博弈中使用Shapley值的社会福利最大化
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929212
Siyuan Chen, Wei Liu, J. Liu, Khí-Uí Soo, Wu Chen
{"title":"Maximizing Social Welfare in Fractional Hedonic Games using Shapley Value","authors":"Siyuan Chen, Wei Liu, J. Liu, Khí-Uí Soo, Wu Chen","doi":"10.1109/AGENTS.2019.8929212","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929212","url":null,"abstract":"Fractional hedonic games (FHGs) are extensively studied in game theory and explain the formation of coalitions among individuals in a group. This paper investigates the coalition generation problem, namely, finding a coalition structure whose social welfare, i.e., the sum of the players’ payoffs, is maximized. We focus on agent-based methods which set the decision rules for each player in the game. Through repeated interactions the players arrive at a coalition structure. In particular, we propose CFSV, namely, coalition formation with Shapley value-based welfare distribution scheme. To evaluate CFSV, we theoretically demonstrate that this algorithm achieves optimal coalition structure over certain standard graph classes and empirically compare the algorithm against other existing benchmarks on real-world and synthetic graphs. The results show that CFSV is able to achieve superior performance.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124665747","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}
引用次数: 1
On Design and Implementation a Federated Chat Service Framework in Social Network Applications 社交网络应用中联邦聊天服务框架的设计与实现
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929183
Shi-Cho Cha, Zhuo-Xun Li, Chuan-Yen Fan, Mila Tsai, Je-Yu Li, Tzu-Chia Huang
{"title":"On Design and Implementation a Federated Chat Service Framework in Social Network Applications","authors":"Shi-Cho Cha, Zhuo-Xun Li, Chuan-Yen Fan, Mila Tsai, Je-Yu Li, Tzu-Chia Huang","doi":"10.1109/AGENTS.2019.8929183","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929183","url":null,"abstract":"As many organizations deploy their chatbots on social network applications to interact with their customers, a person may switch among different chatbots for different services. To reduce the switching cost, this study proposed the Federated Chat Service Framework. The framework maintains user profiles and historical behaviors. Instead of deploying chatbots, organizations follow the rules of the framework to provide chat services. Therefore, the framework can organize service requests with context information and responses to emulate the conversations between users and chat services. Consequently, the study can hopefully contribute to reducing the cost for a user to communicate with different chatbots.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116700322","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}
引用次数: 2
Reinforcement Learning with an Extended Classifier System in Zero-sum Markov Games 零和马尔可夫博弈中扩展分类器系统的强化学习
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929148
Chang Wang, Hao Chen, Chao Yan, Xiaojia Xiang
{"title":"Reinforcement Learning with an Extended Classifier System in Zero-sum Markov Games","authors":"Chang Wang, Hao Chen, Chao Yan, Xiaojia Xiang","doi":"10.1109/AGENTS.2019.8929148","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929148","url":null,"abstract":"A reinforcement learning (RL) agent can learn how to win against an opponent agent in zero-sum Markov Games after episodes of training. However, it is still challenging for the RL agent to acquire the optimal policy if the opponent agent is also able to learn concurrently. In this paper, we propose a new RL algorithm based on the eXtended Classifier System (XCS) that maintains a population of competing rules for action selection and uses the genetic algorithm (GA) to evolve the rules for searching the optimal policy. The RL agent can learn from scratch by observing the behaviors of the opponent agent without making any assumptions about the policy of the RL agent or the opponent agent. In addition, we use eligibility trace to further speed up the learning process. We demonstrate the performance of the proposed algorithm by comparing it with several benchmark algorithms in an adversarial soccer game against the same deterministic policy learner.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114707551","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}
引用次数: 2
Development of Wide Area Distributed Backup System by Using Agent Framework DASH 利用Agent框架DASH开发广域分布式备份系统
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929158
Yafei Zhou, Takahiro Uchiya, Somayya Madakam
{"title":"Development of Wide Area Distributed Backup System by Using Agent Framework DASH","authors":"Yafei Zhou, Takahiro Uchiya, Somayya Madakam","doi":"10.1109/AGENTS.2019.8929158","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929158","url":null,"abstract":"With the popularity of digital technology, digitization of data files has become extremely common, for ensuring safety and convenience of data storage, geographically dispersed and distributed backup systems are widely used for individuals. But individuals are sensitive to storage capacity in most situation, this research will adopt duplication exclusion technique, to avoid excessive storage of duplicate data, ultimately achieve savings in storage capacity. The effectiveness of proposal will be verified through experiment.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129020777","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}
引用次数: 1
Photo Cropping via Deep Reinforcement Learning 通过深度强化学习进行照片裁剪
2019 IEEE International Conference on Agents (ICA) Pub Date : 2019-10-01 DOI: 10.1109/AGENTS.2019.8929167
Yaqing Zhang, Xueming Li, Xuewei Li
{"title":"Photo Cropping via Deep Reinforcement Learning","authors":"Yaqing Zhang, Xueming Li, Xuewei Li","doi":"10.1109/AGENTS.2019.8929167","DOIUrl":"https://doi.org/10.1109/AGENTS.2019.8929167","url":null,"abstract":"Automatic image cropping aims at changing the composition of images to improve the aesthetic quality of images. It can provide professional advice for image editors and save time. Most of the existing automatic image cropping methods are based on specific features such as aesthetic features or salient features. These methods adopt sliding window mechanism to generate numerous cropping candidates, and then select the final results based on these specific features. It is very time-consuming and can only produce cropping results of a limited aspect ratio. In the face of these situations, a DLRL (deep learning framework combined with reinforcement learning) framework is proposed for image cropping, which only uses the basic features of the image for cropping without producing numerous candidate windows. Moreover, cropping step by step is more in line with the process of image cropping by people using Photoshop or other software. Experiments show that the proposed method can save a lot of time and improve cropping efficiency. The method proposed achieves the state-of-art performance in the open Flickr Cropping Dataset and CUHK Image Cropping Dataset.","PeriodicalId":235878,"journal":{"name":"2019 IEEE International Conference on Agents (ICA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122323319","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}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信