{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T13:50:44Z","timestamp":1777038644380,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"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":[[2023,12,10]]},"DOI":"10.1109\/wsc60868.2023.10408462","type":"proceedings-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T13:30:14Z","timestamp":1706707814000},"page":"2357-2367","source":"Crossref","is-referenced-by-count":5,"title":["Incorporation of Military Doctrines and Objectives into an AI Agent Via Natural Language and Reward in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Michael","family":"M\u00f6bius","sequence":"first","affiliation":[{"name":"Airbus Defence and Space GmbH,Dept. Operational Analysis and Studies Claude-Dornier-Strasse,Immenstaad,Germany,88090"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kallfass","sequence":"additional","affiliation":[{"name":"Airbus Defence and Space GmbH,Dept. Operational Analysis and Studies Claude-Dornier-Strasse,Immenstaad,Germany,88090"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Flock","sequence":"additional","affiliation":[{"name":"Airbus Defence and Space GmbH,Dept. Operational Analysis and Studies Claude-Dornier-Strasse,Immenstaad,Germany,88090"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Doll","sequence":"additional","affiliation":[{"name":"UAbt PlgStrg\/Int,Joint Support Service Command Abt Plg,Bonn,Germany,53123"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dietmar","family":"Kunde","sequence":"additional","affiliation":[{"name":"German Army Headquarters von-Hardenberg-Kaserne,Strausberg,Germany,15344"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619093"},{"key":"ref2","article-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref3","article-title":"From the Game Map to the Battlefield - Using DeepMind\u2019s Advanced AlphaStar Techniques to Support Military Decision-Makers","volume-title":"Proceedings of the NATO MSG-184 Symposium","author":"Doll"},{"key":"ref4","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SAUPEC\/RobMech\/PRASA52254.2021.9377018"},{"key":"ref6","article-title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","author":"Gupta","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2005.1574362"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref11","article-title":"A Multi-Head Model for Continual Learning via Out-of-Distribution Replay","author":"Kim","year":"2022"},{"key":"ref12","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WSC57314.2022.10015234"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1207\/S15327876MP1501_01"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref16","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"1998"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref18","article-title":"Attention Is All You Need","volume-title":"Proceedings of 31st Conference on Neural Information Processing Systems","author":"Vaswani"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","article-title":"Automated Cyber Defence: A Review","author":"Vyas","year":"2023"},{"key":"ref21","article-title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","author":"Wang","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3935816"}],"event":{"name":"2023 Winter Simulation Conference (WSC)","location":"San Antonio, TX, USA","start":{"date-parts":[[2023,12,10]]},"end":{"date-parts":[[2023,12,13]]}},"container-title":["2023 Winter Simulation Conference (WSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10406299\/10407113\/10408462.pdf?arnumber=10408462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T19:23:10Z","timestamp":1706815390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10408462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/wsc60868.2023.10408462","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]}}}