{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:51:20Z","timestamp":1729637480233,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"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":[[2021,8,17]]},"DOI":"10.1109\/cog52621.2021.9619104","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:53:06Z","timestamp":1638910386000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Inventory Management with Attention-Based Meta Actions"],"prefix":"10.1109","author":[{"given":"Keisuke","family":"Izumiya","sequence":"first","affiliation":[{"name":"Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan"}]},{"given":"Edgar","family":"Simo-Serra","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Computer Science and Communications Engineering,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref31","article-title":"TorchBeast: A PyTorch Platform for Distributed RL","author":"k\u00fcttler","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231907"},{"key":"ref10","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref12","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref13","first-page":"72","article-title":"Efficient selectivity and backup operators in monte-carlo tree search","author":"coulom","year":"2006","journal-title":"International conference on computers and games"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1609\/aiide.v15i1.5237","article-title":"Improving deep reinforcement learning in minecraft with action advice","volume":"15","author":"frazier","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref15","article-title":"The MineRL competition on sample efficient reinforcement learning using human priors","author":"guss","year":"2019","journal-title":"NeurIPS Competition Track"},{"key":"ref16","article-title":"Neurips 2020 competition: The MineRL competition on sample efficient reinforcement learning using human priors","author":"guss","year":"2020","journal-title":"NeurIPS Competition Track"},{"key":"ref17","article-title":"Rogueinabox: an environment for roguelike learning","volume":"2","author":"asperti","year":"2017","journal-title":"International Journal of Computers"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848075"},{"key":"ref19","first-page":"362","article-title":"A modular deep-learning environment for rogue","volume":"12","author":"asperti","year":"2017","journal-title":"WSEAS Trans Syst Control"},{"key":"ref28","article-title":"The NetHack Learning Environment","author":"k\u00fcttler","year":"0","journal-title":"Proceedings of the Conference on Neural Information Processing Systems (Ne u rIPS)"},{"journal-title":"Berlin interpretation","year":"0","key":"ref4"},{"key":"ref27","article-title":"Deep reinforcement learning with relational inductive biases","author":"zambaldi","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi -agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref6","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref29","article-title":"Environmental drivers of systematicity and generalization in a situated agent","author":"hill","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of The 33rd International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref8","first-page":"2263","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","volume":"4","author":"espeholt","year":"0","journal-title":"ICML 2018-35th International Conference on Machine Learning"},{"key":"ref7","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-13709-0_22"},{"key":"ref22","first-page":"16","article-title":"Learning combat in NetHack","author":"campbell","year":"2017","journal-title":"Thirteenth Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2017)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2899159"},{"key":"ref24","article-title":"Structured attention networks","author":"kim","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref23","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref25","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2021 IEEE Conference on Games (CoG)","start":{"date-parts":[[2021,8,17]]},"location":"Copenhagen, Denmark","end":{"date-parts":[[2021,8,20]]}},"container-title":["2021 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9618888\/9618891\/09619104.pdf?arnumber=9619104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T15:44:20Z","timestamp":1673970260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9619104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cog52621.2021.9619104","relation":{},"subject":[],"published":{"date-parts":[[2021,8,17]]}}}