Akiko Ikenaga, Sachiyo Arai : Estimating Objective Weights of Pareto-Optimal Policies for Multi-Objective Sequential Decision-Making, Journal of Advanced Computational Intelligence and Intelligent Informatics (pp.393-402), (2024.2), https://doi.org/10.20965/jaciii.2024.p0393
Masaharu Saito, Sachiyo Arai : Estimation of Different Reward Functions Latent in Trajectory Data, Journal of Advanced Computational Intelligence and Intelligent Informatics (pp.403-412), (2024.2), https://doi.org/10.20965/jaciii.2024.p0403
Daiko Kishikawa, Sachiyo Arai : Neural scalarisation for multi-objective inverse reinforcement learning, SICE Journal of Control, Measurement, and System Integration (Volume 16, pp140-151), (2023.12), https://doi.org/10.1080/18824889.2023.2194234/
Takumi Saiki, Sachiyo Arai : Flexible Traffic Signal Control via Multi-Objective Reinforcement Learning, IEEE Access (Volume 11, pp.75875-75883), (2023.7),https://doi.org/10.1109/ACCESS.2023.3296537
Dan Zhou, Jiqing Du, Sachiyo Arai : Efficient search of decision makers’ region of interest by using preference directions in multi-objective coevolutionary algorithm, Swarm and Evolutionary Computation (Volume 81, 101349), (2023.6),https://doi.org/10.1016/j.swevo.2023.101349
Dan Zhou, Jiqing Du, Sachiyo Arai : Efficient Elitist Cooperative Evolutionary Algorithm for Multi-Objective Reinforcement Learning, IEEE Access (Volume 11, pp.43128-43139), (2023.5),https://doi.org/10.1109/ACCESS.2023.3272115
Daiko Kishikawa, Sachiyo Arai : Neural scalarisation for multi-objective inverse reinforcement learning, SICE Journal of Control, Measurement, and System Integration (Latest Articles), (2023.4),https://doi.org/10.1080/18824889.2023.2194234
Naoya Takayama, Sachiyo Arai : Multi-objective deep inverse reinforcement learning for weight estimation of objectives, Journal: Artificial Life and Robotics (Volume 27, pp.594-602), (2022.8),https://doi.org/10.1007/s10015-022-00773-8
Daiko Kishikawa and Sachiyo Arai: Estimation of personal driving style via deep inverse reinforcement learning, Journal: Artificial Life and Robotics (Volume 26, issue3, pp.338-346), (2021.8),https://doi.org/10.1007/s10015-021-00682-2
Yasuhiro Yoshida, Sachiyo Arai, Hiroyasu Kobayashi, Keiichiro Kondo : Charge/Discharge Control of Wayside Batteries via Reinforcement Learning for Energy-Conservation in Electrified Railway Systems, Journal: Electrical Engineering Japan, (2021.1), https://doi.org/10.1002/eej.23319
石川翔太,荒井幸代,先行車情報の共有が自然渋滞に与える影響の解析-Nagel-Schreckenberg Model の一般化-,人工知能学会論文誌, Vol.31,No.2,pp. D-F32_1-8 (2016). http://doi.org/10.1527/tjsai.D-F32
Sachiyo Arai, Kanako Suzuki, Encouragement of Right Social Norms by Inverse Reinforcement Learning. Journal of Information Processing, 22(2): pp.299-306, (2014), https://doi.org/10.2197/ipsjjip.22.299
加賀谷 駿,荒井幸代,太陽光発電の変動抑制に向けた強化学習エージェントモデル,電子情報通信学会 和文論文誌D , 情報・システム J96-D, No.12, pp. 3000-3008, (2013).
許 海遅,荒井 幸代,学習ペースカーによるメタ安定相への遷移の実現, 電気学会論文誌C,Vol.133 No.9 pp. 1709-1716, DOI: 10.1541/ieejeiss.133. (2013).
Sachiyo Arai, and Tatsuya Masubuchi, A Study of Traffic Flow Optimization by Learning Pace-car : International Journal of Advancements in Computing Technology, 2012; 4(22), pp. 257-268 (2012).
内田 英明,藤井 秀樹,吉村 忍,荒井 幸代,道路ネットワークの変化に対する経路選択の学習:情報処理学会論文誌,53(11), pp. 2409-2418, 2012-11-15
齋竹良介,竹木祥太,荒井幸代. 期待報酬ベクトルの非線形スカラー化による多目的強化学習アルゴリズム: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 197--204, (2017.9).
本木雄斗,吉永和史,荒井幸代. 逆強化学習による最適な報酬と特徴空間設計に向けた実験的考察: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 298-304, (2017.9).
荒井幸代,今宿誠己,檜山達矢,ステークホルダ同定による空間ゲームの協調の実現: Joint Agent Workshops and Symposium 2010,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催, CD-ROM (2010).
増渕達也,荒井幸代,学習ペースカーによる交通流の最適化と考察: Joint Agent Workshops and Symposium 2010,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2010).
角井勇哉, 荒井幸代, マッチング問題への定型化による最適ラインナップ構成法: Joint Agent Workshops and Symposium 2009,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2009).
大久保 有基,荒井 幸代,エレベータ群制御における呼び対応の公平化を目的とした優先度学習法: Joint Agent Workshops and Symposium 2009,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催, CD-ROM (2009).
増渕達也,荒井幸代,渋滞発生過程におけるメタ安定相の特徴の分析: Joint Agent Workshops and Symposium 2008,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2008).優秀論文賞
今宿誠己,荒井幸代,避難所配置問題における市民位置情報の不完全性の影響: Joint Agent Workshops and Symposium 2008,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2008).
高橋篤,荒井幸代,須貝康雄,コミュニティ概念の定式化: Joint Agent Workshops and Symposium 2008,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2008).
石垣圭久,荒井幸代,情報量によるマルチエージェント系強化学習過程の解析, Joint Agent Workshops and Symposium 2007 電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会,IEEE Computer Society Japan Chapter 主催,CD-ROM (2007). 優秀論文賞
International Conference(more than two reviewers)
Cheng Liu and Sachiyo Arai, On-time and Energy-saving Optimization of Train Auto Driving Based on Reinforcement Learning, Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, Himeji, Japan, (2024.11.9-11)
Daiko Kishikawa and Sachiyo Arai, Multi-Objective Deep Inverse Reinforcement Learning through Direct Weights and Rewards Estimation, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE), Kumamoto, Japan, (2022.9.6-9),DOI: 10.23919/SICE56594.2022.9905799
Daiko Kishikawa and Sachiyo Arai, Multi-Objective Deep Inverse Reinforcement Learning through Direct Weights and Rewards Estimation, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE), Kumamoto, Japan, (2022.9.6-9),DOI: 10.23919/SICE56594.2022.9905799
Takumi Saiki and Sachiyo Arai, Switching Policies based on Multi-Objective Reinforcement Learning for Adaptive Traffic Signal Control, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE), Kumamoto, Japan, (2022.9.6-9),DOI: 10.23919/SICE56594.2022.9905836
Naoya Takayama and Sachiyo Arai, Learning objective weights with adversarial inverse reinforcement learning, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE), Kumamoto, Japan, (2022.9.6-9)
Yusuke Yashiro, Kazuki Eguchi, Rintaro Imamura, Sachiyo Arai, Development of Applicable Reinforcement Learning Compensator Using Ranking Information for AUV, OCEANS 2022, Chennai, India, (2022.2.21-24), DOI: 10.1109/OCEANSChennai45887.2022.9775527
Rintaro Imamura and Sachiyo Arai, Improving robustness via sharpness-aware deep reinforcement learning, AROB2022 - 27th International Symposium on Artificial Life and Robotics, Online, (2022.1.25-27).
Ayumu Mimata and Sachiyo Arai, Real-time detection of suspicious behavior based on estimated value of ordinary's in public space, AROB2022 - 27th International Symposium on Artificial Life and Robotics, Online, (2022.1.25-27).
Naoya Takayama and Sachiyo Arai, Estimating weight of each objective for multi-objective sequential decision-making in continuous state space, AROB2022 - 27th International Symposium on Artificial Life and Robotics, Online, (2022.1.25-27) .
Dan Zhou, Jiqing Du and Sachiyo Arai, Multi-objective coevolutionary algorithm based on preference direction, AROB2022 - 27th International Symposium on Artificial Life and Robotics, Online, (2022.1.25-27) .
Daiko Kishikawa and Sachiyo Arai, Multi-Objective Inverse Reinforcement Learning via Non-Negative Matrix Factorization, 10th International Congress on Advanced Applied Informatics / 9th International Conference on Smart Computing and Artificial Intelligence, Online, (2021.7.12).
Yusuke Nakata and Sachiyo Arai, Mini-batch Bayesian Inverse Reinforcement Learning for Multiple Dynamics, Proceedings of the 19th International Conference on Autonomous Agent and Multiagent Systems, pp.1949-1950, May 2020, Auckland, New Zealand, (2020). https://dl.acm.org/doi/abs/10.5555/3398761.3399037
Toshiaki Chimura,Sachiyo Arai,Ranking method of suboptimal trajectories for inverse reinforcement learning, AROB2020 - 25th International Symposium on Artificial Life and Robotics,2020.1,Oita
Daiko Kishikawa and Sachiyo Arai, Comfortable Driving by Using Deep Inverse Reinforcement Learning, The 4th IEEE International Conference on Agents (ICA 2019), 18-21, October, 2019 at Jinan, China, (2019).
Kousuke Nishi and Sachiyo Arai, Modeling Multi-objectivization Mechanism in Multi-agent Domain, The 4th IEEE International Conference on Agents (ICA 2019), 18-21, October, 2019 at Jinan, China, (2019).
Toya Kamatani, Yusuke Nakata and Sachiyo Arai, Dynamic Pricing Method to Maximize Utilization of One-way Car Sharing Service, The 4th IEEE International Conference on Agents (ICA 2019), 18-21, October, 2019 at Jinan, China, (2019).
Keiichi Namikoshi and Sachiyo Arai, Estimation of agent's rewards using multi-agent maximum discounted causal entropy inverse reinforcement learning, Adaptive and Learning Agents Workshop at AAMAS, Montreal, Canada, 13 - 14 May 2019.
Yusuke Nakata and Sachiyo Arai, Bayesian Inverse Reinforcement Learning for Expert's Demonstrations in Multiple Dynamics, Adaptive and Learning Agents Workshop at AAMAS, Montreal, Canada, 13 - 14 May 2019.
Keiichi Namikoshi and Sachiyo Arai : Estimation of the heterogeneous strategies from action log, The Genetic and Evolutionary Computation Conference (GECCO) '18 Proceedings of the Genetic and Evolutionary Computation Conference, Pages 1310-1317, (July 15 - 19, 2018 Kyoto, Japan), ISBN: 978-1-4503-5618-3 doi>10.1145/3205455.3205639
Ishikawa, S., Arai, S.: Learning Cooperative Policy among Self-Driving Vehicles for Relieving Traffic Jams, Proceeding of the international workshop on Agents in Traffic and Transportation 2018, (July 2018 Sweden)
Yasuhiro Yoshida and Sachiyo Arai, Charge Control of Regenerative Power for Energy Saving in Railway Systems, 2018 The 3rd IEEE International Conference on Agents (ICA 2018) , pp. 69-74, DOI: 10.1109/AGENTS.2018.8460096 (2018). Singapore 28 - 31 July 2018 , IEEE Catalog Number: ISBN: CFP18H09-POD 978-1-5386-8181-7
Akiko Ikenaga and Sachiyo Arai, Inverse Reinforcement Learning Approach for Elicitation of Preferences in Multi-objective Sequential Optimization, 2018 IEEE International Conference on Agents (ICA 2018) , pp. 117-118, DOI: 10.1109/AGENTS.2018.8460075, (2018). Singapore 28 - 31 July 2018 , IEEE Catalog Number: ISBN: CFP18H09-POD 978-1-5386-8181-7
Yusuke Nakata, Yuki Kitazato and Sachiyo Arai, Detection of Features Affording a Certain Action via Analysis of CNN, 2018 IEEE International Conference on Agents (ICA 2018) , pp.105-108, DOI: 10.1109/AGENTS.2018.8460062 ,(2018). Singapore 28 - 31 July 2018 , IEEE Catalog Number: ISBN: CFP18H09-POD 978-1-5386-8181-7
Yuki Kitazato, Sachiyo Arai, Estimation of reward function maximizing learning efficiency in inverse reinforcement learning, 10th International Conference on Agents and Artificial Intelligence, pp. 276 -283, (2018) DOI: 10.5220/0006729502760283 )
Shota Ishikawa,Sachiyo Arai, Cooperative Learning of a Driving Strategy to Suppress Phantom Traffic Jams, IEEE International Conference on Agents, pp.90-93, ISBN: 978-1-5090-3931-9,DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICA.2016.029, (2016. 9.30 Matsue, Japan)
Ryosuke Saitake, Sachiyo Arai, Parameter Estimation of Multi-Objective Reinforcement Learning to Reach Arbitrary Pareto Solution, IEEE International Conference on Agents, pp.110-111, (2016. 9.30 Matsue, Japan)
Sachiyo Arai, Haichi Xu: Faster Convergence to Cooperative Policy by Autonomous Detection of Interference States in Multiagent Reinforcement Learning. PRICAI 2016: 16-29, (2016. 8.22-26, Phuket, Thailand), Lecture Notes in Computer Science Book series (LNCS, volume 9810), pp. 16-29
Shota Ishikawa,Sachiyo Arai,Evaluating Advantage of Sharing Information among Vehicles Toward Avoiding Phantom Traffic Jam, Proceedings of the 2015 Winter Simulation Conference,pp.300-311, (2015.12 USA).
Hino, Y., Arai, S., "Avoid the Overflow of Disaster Victims around the Railway Station -via Adaptive Management of Passengers' Routes and Train Schedule-", RailTokyo2015, 10 pages, (2015.3 Japan).
Sachiyo Arai, and Tatsuya Masubuchi, A Study of Traffic Flow Optimization by Learning Pace-car, The 15th Asia Pacific Symposium on Intelligent and Evolutionary Systems, 6 pages, (2011).
Sachiyo Arai, Yuta Mabuchi, Learning Strategic Information Support for Controlling Traffic Flow, International Conference on Intelligent Unmanned Systems, 6 pages, (2011).
Shuichiro Kanno, and Sachiyo Arai, Interaction Model for Chasm Creation on Multiagent Network, The SICE Annual Conference 2011, 6 pages, (2011).
Yuya Kakui, Sachiyo Arai, Scene Evaluation of a Ball Game for Solving Batting Order Optimization, The SICE Annual Conference 2010, 6 pages, (2010).
Masaki Imajuku, Tatsuya Hiyama, Sachiyo Arai, A Preliminary Analysis of Interactive Effects between Network Structure and Decision Criteria on the Global Behavior, ICROS-SICE International Joint Conference 2009, 6 pages , (2009).
Atsuko Takano, Kazuko Takagi, Sachiyo Arai, Hiroya Takeuchi and Syun Tutiya, CURATOR:its developmental strategy, International Conference on Open Repositories, pp.23-27,(2007).
Nobuyuki Tanaka and Sachiyo Arai,Teamwork Formation for Keepaway in Robotics Soccer, 9th Pacific Rim International Workshop on Multi-Agents,8 pages, (2006) .
Nobuyuki Tanaka and Sachiyo Arai, Reward Design for Emerging Cooperative Behavior in Continuing Task Domains : International Joint Conference on Autonomous Agents and Multiagent Systems,Workshop on Adaptation and Learning in Autonomous Agents and Multiagent systems,pp. 7-14, (2006).
Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachiyo Arai,Guiding Inference Through Relational Reinforcement Learning, Inductive Logic Programming , pp. 20-37, (2005).
Pat Langley, Sachiyo Arai, and Daniel Shapiro,Model-Based Learning with Hierarchical Relational Skills:International Conference on Machine Learning Workshop on Relational Reinforcement Learning,pp. 63-68 (2004).
Sachiyo Arai and Toru Ishida, Learning for Human-Agent Collaboration on the Semantic Web: International Conference on Informatics Research for Development of Knowledge Society Infrastructure ,pp. 132-139, (2004).
Sachiyo Arai, Yohei Murakami, Yuki Sugimoto and Toru Ishida, Multi-agent Scenarios Introducing Semantics for Web Services, The New Trends on Knowledge Processing -Data Mining, Semantic Web and Computational Science 6, Invited Paper,pp. 1-5, (2003).
Sachiyo Arai, Yohei Murakami, Yuki Sugimoto, Toru Ishida,Semantic Web Service Architecture using Multi-agent Scenario Description:3th Pacific Rim International Conference on Artificial Intelligence, pp.90-109, (2003).
Sachiyo Arai, and Katia Sycara,Credit Assignment Method for Learning Effective Stochastic Policies in Uncertain Domains: GECCO-2001, Proceedings of Genetic and Evolutionary Computation Conference, pp. 815-822, (2001).
Kazuteru Miyazaki, Sachiyo Arai, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Profit Sharing: Proceedings of the 6th International Conference on Information Systems Analysis and Synthesis, pp.178-183, (2000).
Sachiyo Arai, Katia Sycara, and Terry R. Payne, Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multi-agent Domain, Pacific Rim International Conference on Artificial Intelligence, pp.125-135, (2000).
Sachiyo Arai and Katia Sycara,Effective Learning Approach for Planning and Scheduling in Multi-agent Domain: Proceedings of the 6th International Conference on Simulation of Adaptive Behavior (From animals to animats 6), ISAB-2000, pp.507-516, (2000).
Sachiyo Arai and Katia Sycara, Multi-Agent Reinforcement Learning for Planning and Scheduling Multiple Goals, Proceedings of the 4th International Conference on Multi-Agent Systems, pp. 359-360, (2000).
Sachiyo Arai, Shigenobu Kobayashi, Multi-agent Reinforcement Learning for Crane Control Problem : Multi-Agent Reinforcement Learning for Planning and Conflict Resolution in a Dynamic Domain:Designing Rewards for Conflict Resolution, Autonomous Decentralized Systems, pp.310-319 (1999).
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Reinforcement Learning, International Conference on Intelligent Autonomous Systems, Vol.5, pp. 335-342, (1998).
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Learning Cooperative Behavior by Profit Sharing Agents, Proceedings of the 15th International Joint Conference on Artificial Intelligence, p.7, (1997).
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Generating Cooperative Behavior by Multi-Agent Reinforcement Learning, Proceedings of the 6th European Workshop on Learning Robots, pp. 111-120, (1997).
Sachiyo Arai, Rational Balancing of Planning and Communication in the Dynamic Multi-agents World: Proceedings of the 4th International Conference on Autonomous Agents, ICMAS-1995, pp.436-437 (1995).
Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Horizontal and Vertical Cooperation by Multi-agents for Dynamic Planning, Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence, pp.77-82, (1990).
Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Model of Problem Decomposition in Cooperative Planning, Proceedings of the 28th SICE Annual Conference, Vol.2, pp.1255-1258, (1989).
Naoto Horie, Sachiyo Arai, Verification of Autonomous Drone Control System for Gathering Information in Disaster Areas, 2021年度第35回人工知能学会全国大会, 4N2-IS-3b-01, (2021.6.8~11,オンライン).
Daiko Kishikawa, Sachiyo Arai, Deep Inverse Reinforcement Learning with Adversarial One-Class Classification, 2021年度第35回人工知能学会全国大会, 3N3-IS-2e-05, (2021.6.8~11,オンライン).
中田勇介, 荒井幸代. 複数環境におけるエキスパート軌跡を用いたミニバッチベイジアン逆強化学習, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Full paper査読付).IEEE Computer Society Young Researcher Award Nominee, 研究奨励賞.
池永晶子, 荒井幸代. 部分観測下の多目的逐次意思決定問題における各目的の重み推定,Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Full paper査読付).IEEE Computer Society Young Researcher Award, 研究奨励賞.
吉田賢央, 荒井幸代. 深層強化学習による鉄道システムの回生電力活用,Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Full paper 査読付).研究奨励賞.
浪越圭一, 野田五十樹, 荒井幸代. MASモデル構築のためのHeterogeneous swarm逆強化学習の検討, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Late Breaking paper). 最優秀ポスター発表賞.
北村清也, 荒井幸代. 単純なシーンの学習勾配に着目した運転方策の切替え法~市街地の複雑なシーンでの自動運転実現に向けて~, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Late Breaking paper). 優秀ポスター発表賞.
山本慶佑, 荒井幸代. minimax最適化基準を用いたリスク回避方策獲得可能なMORL, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Late Breaking paper).
野村俊太, 荒井幸代. 複数報酬を用いた深層強化学習による自動運転操作の獲得, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Late Breaking paper).
千邑峻明, 荒井幸代. 逆強化学習における準最適な軌跡の定量的評価 ~準最適軌跡比較における効率的計算法~, Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2019予稿集,(2019.9.9~11 大分別府). (Late Breaking paper).
西孝介,荒井幸代,意思行動における嗜好推定に基づく行動制御,Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2018予稿集,(2018.9.13~15 広島).
岸川大航,荒井幸代,深層強化学習におけるアテンション推定による学習行動の精緻化,Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2018予稿集,(2018.9.13~15 広島).
釜谷統哉,荒井幸代,カーシェアリングサービスにおける占有率安定化に向けた料金設定,Joint Agent Workshops and Symposium 2018,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2018予稿集,(2018.9.13~15 広島).
木村祥, 荒井幸代,変分自己符号化器を用いた継続学習における頑健性指標,oint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 309--310, (2017.9.15 千葉).
石川翔太,荒井幸代,熟練ドライバの運転を学習するための報酬と特徴ベクトルの同時推定法,Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 310--311, (2017.9.15 千葉).
浪越圭一, 荒井幸代, 追従エージェントを考慮した人流データからの戦略抽出, Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 319--320, (2017.9.15 千葉).
吉永和史, 北里勇樹,荒井幸代,センサ情報を利用したごみ収集最適化のための強化学習アプローチ,Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 323--324, (2017.9.15 千葉).
吉田賢央,荒井幸代,鉄道システムにおける回生電力蓄電池の充放電制御-強化学習によるアプローチ-, Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 327--328, (2017.9.15 千葉).
山本慶佑,荒井幸代,多目的強化学習によるごみ収集業務のパレート方策の獲得, Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 329--330, (2017.9.15 千葉).
千邑峻明, 荒井幸代,強化学習エージェントによるシグナリングゲームの被験者実験の再現,Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 331--332, (2017.9.15 千葉).
北村清也, 荒井幸代, 市街地自動運転に向けた環境入力データの特徴抽出, Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 339--340, (2017.9.15 千葉).
池永晶子, 石川翔太, 荒井幸代, 意思決定エージェントの多目的に対する選好の推定法, Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 341--342, (2017.9.15 千葉).
齋竹良介,竹木祥太,荒井幸代,期待報酬ベクトルの非線形スカラー化による多目的強化学習アルゴリズム,Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 197--204, (2017.9.15 千葉).
本木雄斗,吉永和史,荒井幸代,逆強化学習による最適な報酬と特徴空間設計に向けた実験的考察,Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援,JAWS2017予稿集 pp. 298-304, (2017.9.16 千葉).
高澤知也,荒井幸代,須貝康雄, ネットワーク生成モデルを用いたコミュニティ抽出法の考察, 計測自動制御学会システム・情報部門, 第19回 自律分散システムシンポジウム講演論文集, pp. 301-306, (2007).
高橋篤,荒井幸代, 最小カットを用いたネットワーククラスタリング手法の考察, 計測自動制御学会システム・情報部門, 第19回 自律分散システムシンポジウム講演論文集, pp. 295-300, (2007).
Nobuyuki Tanaka and Sachiyo Arai,Teamwork Formation for Keepaway in Robotics Soccer (Reinforcement Learning Approach), Ninth Pacific Rim International Workshop on Multi-Agents,(2006).
荒井幸代,須貝康雄, 強化学習エージェント間の相互関係性の抽出, 平成17年 電気学会, 電子・情報・システム部門大会講演論文集, 電気学会, pp. 1029-1034, (2005).
荒井幸代 and Pat Langley, 環境モデルに基づく弱-強化学習, Joint Agent Workshops and Symposium 2010, JAWS-2004 講演論文集, pp. 371-378, (2004) .
Sachiyo Arai, Yohei Murakami, Yuki Sugimoto, Toru Ishida, Semantic Web Service Architecture using Multi-agent Scenario Description, 6th Pacific Rim International Workshop on Multi-Agents, pp.98-109, (2003).
Zhiqiang Gao, Sachiyo Arai and Toru Ishida, Social Agents in Digital Cities. Agent cities: Challenges in Open Agent Environments, (2003) .
Sachiyo Arai and Kazuteru Miyazaki, Learning Robust Policies for Uncertain and Stochastic Multi-agent Domains, International Symposium on Artificial Life and Robotics, (2002).
Sachiyo Arai and Katia Sycara, Multi-Agent Reinforcement Learning for Planning and Conflict Resolution in a Dynamic Domain, Proceedings of the 4th International Conference on Autonomous Agents , pp. 104-105, (2000).
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Cranes Control Using Multi-agent Reinforcement Learning, International Conference on Intelligent Autonomous Systems, Vol.5, pp. 335-342, (1998).
宮崎和光,荒井幸代,小林重信, 強化学習によるエレベータ群およびクレーン群の制御,システム制御学会, 離散事象システムシンポジウム講演資料集, pp. 55-62, (1998).
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Learning Cooperative Behavior by Profit Sharing Agents, Proceedings of the 15th International Joint Conference on Artificial Intelligence, p.7, (1997)
Sachiyo Arai, Kazuteru Miyazaki, and Shigenobu Kobayashi, Generating Cooperative Behavior by Multi-Agent Reinforcement Learning, Proceedings of the 6th European Workshop on Learning Robots, pp. 111-120, (1997) .
荒井幸代,山村雅幸,小林重信, 動的環境下における強化学習型マルチエージェント系の協調,人工知能学会, 第9回全国大会論文集, pp. 139-142, (1995).
荒井幸代,小林重信, 動的環境下での適応的プランニングのための複数エージェント協調モデル, 計測自動制御学会システム・情報部門, 第12回知能システムシンポジウム講演資料集 pp. 69-74, (1990).
Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Horizontal and Vertical Cooperation by Multi-agents for Dynamic Planning, Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence, pp.77-82, (1990).
Sachiyo Arai, Masayuki Yamamura, and Shigenobu Kobayashi, Model of Problem Decomposition in Cooperative Planning, Proceedings of the 28th SICE Annual Conference, Vol.2, pp.1255-1258, (1989).
Multiagent Applications with Evolutionary Computation and Biologically Inspired Technologies: Intelligent Techniques for Ubiquity and Optimization. IGI GLOBAL, 分担執筆,(2010.8).
Intelligent Autonomous Systems,- Learning - : Cranes Control Using Multi-agent Reinforcement Learning,Yukinori Kakazu eds. 分担執筆, IOS Press,(1998.3).
令和3年7月:10th International Congress on Advanced Applied Informatics / 9th International Conference on Smart Computing and Artificial Intelligence: Competitive Paper Award, Daiko Kishikawa and Sachiyo Arai, Multi-Objective Inverse Reinforcement Learning via Non-Negative Matrix Factorization.
令和元年10月: The 4th IEEE International Conference on Agents :Best student paper award, Daiko Kishikawa and Sachiyo Arai, Comfortable Driving by Using Deep Inverse Reinforcement Learning.
令和元年10月: IEEE Computer Society Japan Chapter JAWS Young Researcher Award, 池永晶子,荒井幸代:部分観測下の多目的逐次意思決定問題における各目的の重み推定.
令和元年9月: Joint Agent Workshops and Symposium 2019,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 研究奨励賞, 対象論文:中田勇介,荒井幸代:複数環境におけるエキスパート軌跡を用いたミニバッチベイジアン逆強化学習.
令和元年9月: Joint Agent Workshops and Symposium 2019,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 研究奨励賞, 吉田賢央,荒井幸代:深層強化学習による鉄道システムの回生電力活用.
令和元年9月: Joint Agent Workshops and Symposium 2019,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 研究奨励賞, 池永晶子,荒井幸代:部分観測下の多目的逐次意思決定問題における各目的の重み推定.
令和元年9月: Joint Agent Workshops and Symposium 2019,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 最優秀発表賞, 対象論文:浪越圭一,野田五十樹,荒井幸代:MASモデル構築のためのHeterogeneous swarm逆強化学習の検討.
令和元年9月: Joint Agent Workshops and Symposium 2019,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀発表賞, 対象論文:北村清也,荒井幸代:単純なシーンの学習勾配に着目した運転方策の切替え法,~市街地の複雑なシーンでの自動運転実現に向けて~ .
平成29年9月: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀論文賞, 対象論文:齋竹良介, 竹木祥太, 荒井幸代. 期待報酬ベクトルの非線形スカラー化による多目的強化学習アルゴリズム.
平成29年9月: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀ポスター発表優秀賞, 対象論文:浪越圭一,荒井幸代,追従エージェントを考慮した人流データからの戦略抽出.
平成29年9月: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀ポスター発表優秀賞, 対象論文:石川翔太,荒井幸代,熟練ドライバの運転を学習するための報酬と特徴ベクトルの同時推定法.
平成28年9月: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀発表優秀賞, 対象論文:中田勇介,荒井幸代,深層学習の中間層の解析に基づくアフォーダンスの設計に有用な特徴の抽出.
平成28年9月: Joint Agent Workshops and Symposium 2017,電子情報通信学会,日本ソフトウェア学会,情報処理学会,人工知能学会共催,IEEE Computer Society Japan Chapter後援, 優秀ポスター発表優秀賞, 対象論文:浪越圭一,荒井幸代,追従エージェントを考慮した人流データからの戦略抽出.