{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:20:48Z","timestamp":1763018448530,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534363","type":"proceedings-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T18:32:08Z","timestamp":1632421928000},"page":"1-10","source":"Crossref","is-referenced-by-count":22,"title":["Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hidenori","family":"Itaya","sequence":"first","affiliation":[{"name":"Chubu University,Kasugai,Aichi,Japan"}]},{"given":"Tsubasa","family":"Hirakawa","sequence":"additional","affiliation":[{"name":"Chubu University,Kasugai,Aichi,Japan"}]},{"given":"Takayoshi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Chubu University,Kasugai,Aichi,Japan"}]},{"given":"Hironobu","family":"Fujiyoshi","sequence":"additional","affiliation":[{"name":"Chubu University,Kasugai,Aichi,Japan"}]},{"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University,Yokohama,Kanagawa,Japan"}]}],"member":"263","reference":[{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref32"},{"key":"ref31","first-page":"802","article-title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","author":"xingjian","year":"2015","journal-title":"Proceedings of Neural Information Processing Systems (NeurIPS)"},{"key":"ref30","first-page":"12 350","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume":"32","author":"mott","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"ref13","article-title":"Deep attention recurrent q-network","author":"sorokin","year":"2015","journal-title":"Proceedings of neural information processing systems (NeurIPS) workshops"},{"key":"ref14","first-page":"1792","article-title":"Visualizing and understanding Atari agents","volume":"80","author":"greydanus","year":"2018","journal-title":"Proceedings of International Conference on Machine Learning (ICML)"},{"key":"ref15","article-title":"Deep Reinforcement Learning with Double Q- Learning","author":"van hasselt","year":"2016","journal-title":"AAAI Conf on Artif Intell (AAAI)"},{"key":"ref16","first-page":"1995","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref17","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"AAAI Conf on Artif Intell (AAAI)"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10744","article-title":"A deep hierarchical approach to lifelong learning in Minecraft","author":"tessler","year":"2017","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"journal-title":"A Survey of Deep Reinforcement Learning in Video Games","year":"2019","author":"shao","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_41"},{"journal-title":"Deep Learning for Video Game Playing","year":"2017","author":"justesen","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref21"},{"key":"ref24","article-title":"Mas-sively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"Deep Learning Workshop International Conference on Machine Learning (ICML)"},{"key":"ref23","first-page":"1008","article-title":"Actor-Critic Algorithms","author":"konda","year":"2000","journal-title":"Proceeding of neural information processing systems (NeurIPS)"},{"key":"ref26","article-title":"Recurrent Experience Replay in Distributed Reinforcement Learning","author":"kapturowski","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref25","article-title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","author":"jaderberg","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534363.pdf?arnumber=9534363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T20:38:14Z","timestamp":1673296694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534363","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}