{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:28:12Z","timestamp":1783787292868,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,6]]},"DOI":"10.1145\/3689933.3690835","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:26:07Z","timestamp":1731003967000},"page":"56-67","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Entity-based Reinforcement Learning for Autonomous Cyber Defence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7908-4107","authenticated-orcid":false,"given":"Isaac","family":"Symes Thompson","sequence":"first","affiliation":[{"name":"The Alan Turing Institute, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5643-2302","authenticated-orcid":false,"given":"Alberto","family":"Caron","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-004X","authenticated-orcid":false,"given":"Chris","family":"Hicks","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2667-5906","authenticated-orcid":false,"given":"Vasilios","family":"Mavroudis","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Alberto Acuto and Simon Maskell. 2023. Defending the unknown: Exploring reinforcement learning agents' deployment in realistic unseen networks."},{"key":"e_1_3_2_1_2_1","unstructured":"Alex Andrew Sam Spillard Joshua Collyer and Neil Dhir. 2022. Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation. arxiv: 2207.12355 [cs.CR]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560830.3563732"},{"key":"e_1_3_2_1_4_1","volume-title":"Generalising Discrete Action Spaces with Conditional Action Trees. 2021 IEEE Conference on Games (CoG)","author":"Bamford Christopher","year":"2021","unstructured":"Christopher Bamford and Alvaro Ovalle. 2021. Generalising Discrete Action Spaces with Conditional Action Trees. 2021 IEEE Conference on Games (CoG) (2021), 1--8. https:\/\/api.semanticscholar.org\/CorpusID:233240936"},{"key":"e_1_3_2_1_5_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Bello Irwan","year":"2017","unstructured":"Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, and Samy Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=Bk9mxlSFx"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004--3702(00)00033--3"},{"key":"e_1_3_2_1_7_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arxiv: 1606.01540 [cs.LG]"},{"key":"e_1_3_2_1_8_1","unstructured":"David Choi. 2020. AlphaStar: Considerations and Human-like Constraints for Deep Learning Game Interfaces. Master's thesis. http:\/\/hdl.handle.net\/10012\/16552"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML 2022), ML4Cyber Workshop","author":"Collyer J.","year":"2022","unstructured":"J. Collyer, A. Andrew, and D. Hodges. 2022. ACD-G: Enhancing Autonomous Cyber Defense Agent Generalization through Graph Embedded Network Representation. In Proceedings of the 39th International Conference on Machine Learning (ICML 2022), ML4Cyber Workshop. Baltimore, Maryland, USA. 17--23 July 2022."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007694015589"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Conference on Applied Machine Learning in Information Security, CAMLIS 2022, Arlington, Virginia, USA, October 20--21, 2022 (CEUR Workshop Proceedings","volume":"19","author":"Foley Myles","year":"2022","unstructured":"Myles Foley, Mia Wang, Zoe M, Chris Hicks, and Vasilios Mavroudis. 2022. Inroads into Autonomous Network Defence using Explained Reinforcement Learning. In Proceedings of the Conference on Applied Machine Learning in Information Security, CAMLIS 2022, Arlington, Virginia, USA, October 20--21, 2022 (CEUR Workshop Proceedings, Vol. 3391). CEUR-WS.org, 1--19. https:\/\/ceur-ws.org\/Vol-3391\/paper1.pdf"},{"key":"e_1_3_2_1_13_1","unstructured":"TTCP CAGE Working Group. 2023. TTCP CAGE Challenge 4. https:\/\/github.com\/cage-challenge\/cage-challenge-4."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1000"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.25080\/TCWV9851"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM50824.2020.9269092"},{"key":"e_1_3_2_1_17_1","volume-title":"Learning Security Strategies through Game Play and Optimal Stopping. 17--23","author":"Hammar Kim","year":"2022","unstructured":"Kim Hammar and Rolf Stadler. 2022. Learning Security Strategies through Game Play and Optimal Stopping. 17--23 July 2022."},{"key":"e_1_3_2_1_18_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uDxeSZ1wdI","author":"Haramati Dan","year":"2024","unstructured":"Dan Haramati, Tal Daniel, and Aviv Tamar. 2024. Entity-Centric Reinforcement Learning for Object Manipulation from Pixels. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uDxeSZ1wdI"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_20_1","volume-title":"Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fy_XRVHqly","author":"Hong Sunghoon","year":"2022","unstructured":"Sunghoon Hong, Deunsol Yoon, and Kee-Eung Kim. 2022. Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fy_XRVHqly"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","volume":"23","author":"Huang Shengyi","year":"2022","unstructured":"Shengyi Huang, Rousslan Fernand Julien Dossa, Chang Ye, Jeff Braga, Dipam Chakraborty, Kinal Mehta, and Jo\u00e3o G.M. Ara\u00fajo. 2022. CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms. Journal of Machine Learning Research, Vol. 23, 274 (2022), 1--18. http:\/\/jmlr.org\/papers\/v23\/21--1342.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML'20)","author":"Huang Wenlong","year":"2020","unstructured":"Wenlong Huang, Igor Mordatch, and Deepak Pathak. 2020. One policy to control them all: shared modular policies for agent-agnostic control. In Proceedings of the 37th International Conference on Machine Learning (ICML'20). JMLR.org, Article 414, 10 pages."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--54129--2_35"},{"key":"e_1_3_2_1_24_1","volume-title":"Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition. arxiv","author":"Janisch Jarom\u00edr","year":"2009","unstructured":"Jarom\u00edr Janisch, Tom\u00e1? Pevn\u00fd, and Viliam Lis\u00fd. 2023. Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition. arxiv: 2009.12462 [cs.LG] https:\/\/arxiv.org\/abs\/2009.12462"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=N3zUDGN5lO","author":"Kurin Vitaly","year":"2021","unstructured":"Vitaly Kurin, Maximilian Igl, Tim Rockt\u00e4schel, Wendelin Boehmer, and Shimon Whiteson. 2021. My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=N3zUDGN5lO"},{"key":"e_1_3_2_1_26_1","unstructured":"Baihan Lin Djallel Bouneffouf and Irina Rish. 2023. A Survey on Compositional Generalization in Applications. arxiv: 2302.01067 [cs.AI] https:\/\/arxiv.org\/abs\/2302.01067"},{"key":"e_1_3_2_1_27_1","unstructured":"Davide Mambelli Frederik Tr\u00e4uble Stefan Bauer Bernhard Sch\u00f6lkopf and Francesco Locatello. 2022. Compositional Multi-Object Reinforcement Learning with Linear Relation Networks. https:\/\/arxiv.org\/abs\/2201.13388"},{"key":"e_1_3_2_1_28_1","volume-title":"Kochenderfer","author":"Mern John","year":"2021","unstructured":"John Mern, Kyle Hatch, Ryan Silva, Jeff Brush, and Mykel J. Kochenderfer. 2021. Reinforcement Learning for Industrial Control Network Cyber Security Orchestration. arxiv: 2106.05332 [cs.CR] https:\/\/arxiv.org\/abs\/2106.05332"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W54100.2022.00015"},{"key":"e_1_3_2_1_30_1","volume-title":"Object Exchangeability in Reinforcement Learning: Extended Abstract. arxiv","author":"Mern John","year":"1905","unstructured":"John Mern, Dorsa Sadigh, and Mykel Kochenderfer. 2019. Object Exchangeability in Reinforcement Learning: Extended Abstract. arxiv: 1905.02698 [cs.LG] https:\/\/arxiv.org\/abs\/1905.02698"},{"key":"e_1_3_2_1_31_1","volume-title":"Kochenderfer","author":"Mern John","year":"2020","unstructured":"John Mern, Dorsa Sadigh, and Mykel J. Kochenderfer. 2020. Exchangeable Input Representations for Reinforcement Learning. arxiv: 2003.09022 [cs.LG] https:\/\/arxiv.org\/abs\/2003.09022"},{"key":"e_1_3_2_1_32_1","unstructured":"Andres Molina-Markham Cory Miniter Becky Powell and Ahmad Ridley. 2021. Network Environment Design for Autonomous Cyberdefense. arxiv: 2103.07583 [cs.CR]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"e_1_3_2_1_34_1","unstructured":"Gregory Palmer Chris Parry Daniel J. B. Harrold and Chris Willis. 2023. Deep Reinforcement Learning for Autonomous Cyber Operations: A Survey. arxiv: 2310.07745 [cs.LG]"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin Antonin","year":"2021","unstructured":"Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. 2021. Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research, Vol. 22, 268 (2021), 1--8. http:\/\/jmlr.org\/papers\/v22\/20--1364.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586094"},{"key":"e_1_3_2_1_37_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv: 1707.06347 [cs.LG]"},{"key":"e_1_3_2_1_38_1","unstructured":"Maxwell Standen David Bowman Son Hoang Toby Richer Martin Lucas and Richard Van Tassel. 2021. Cyber Autonomy Gym for Experimentation Challenge 1. https:\/\/github.com\/cage-challenge\/cage-challenge-1."},{"key":"e_1_3_2_1_39_1","volume-title":"Phillip Vu, and Mitchell Kiely.","author":"Standen Maxwell","year":"2022","unstructured":"Maxwell Standen, David Bowman, Son Hoang, Toby Richer, Martin Lucas, Richard Van Tassel, Phillip Vu, and Mitchell Kiely. 2022. Cyber Autonomy Gym for Experimentation Challenge 2. https:\/\/github.com\/cage-challenge\/cage-challenge-2."},{"key":"e_1_3_2_1_40_1","volume-title":"Phillip Vu, Mitchell Kiely, KC C., Natalie Konschnik, and Joshua Collyer.","author":"Standen Maxwell","year":"2022","unstructured":"Maxwell Standen, David Bowman, Son Hoang, Toby Richer, Martin Lucas, Richard Van Tassel, Phillip Vu, Mitchell Kiely, KC C., Natalie Konschnik, and Joshua Collyer. 2022. Cyber Operations Research Gym. https:\/\/github.com\/cage-challenge\/CybORG."},{"key":"e_1_3_2_1_41_1","unstructured":"Maxwell Standen Martin Lucas David Bowman Toby J. Richer Junae Kim and Damian Marriott. 2021. CybORG: A Gym for the Development of Autonomous Cyber Agents."},{"key":"e_1_3_2_1_42_1","unstructured":"Microsoft Defender Research Team. 2021. CyberBattleSim. https:\/\/github.com\/microsoft\/cyberbattlesim. Created by Christian Seifert Michael Betser William Blum James Bono Kate Farris Emily Goren Justin Grana Kristian Holsheimer Brandon Marken Joshua Neil Nicole Nichols Jugal Parikh Haoran Wei.."},{"key":"e_1_3_2_1_43_1","volume-title":"Tristan Deleu, Manuel Goul ao, Andreas Kallinteris, Markus Krimmel, Arjun KG, et al.","author":"Towers Mark","year":"2024","unstructured":"Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U Balis, Gianluca De Cola, Tristan Deleu, Manuel Goul ao, Andreas Kallinteris, Markus Krimmel, Arjun KG, et al. 2024. Gymnasium: A Standard Interface for Reinforcement Learning Environments. arXiv preprint arXiv:2407.17032 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_45_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019--1724-z"},{"key":"e_1_3_2_1_47_1","unstructured":"Oriol Vinyals Timo Ewalds Sergey Bartunov Petko Georgiev Alexander Sasha Vezhnevets Michelle Yeo Alireza Makhzani Heinrich K\u00fcttler John Agapiou Julian Schrittwieser John Quan Stephen Gaffney Stig Petersen Karen Simonyan Tom Schaul Hado van Hasselt David Silver Timothy Lillicrap Kevin Calderone Paul Keet Anthony Brunasso David Lawrence Anders Ekermo Jacob Repp and Rodney Tsing. 2017. StarCraft II: A New Challenge for Reinforcement Learning. arxiv: 1708.04782 [cs.LG] https:\/\/arxiv.org\/abs\/1708.04782"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer Networks. In Advances in Neural Information Processing Systems, Vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/29921001f2f04bd3baee84a12e98098f-Paper.pdf"},{"key":"e_1_3_2_1_49_1","volume-title":"NerveNet: Learning Structured Policy with Graph Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1sqHMZCb","author":"Wang Tingwu","year":"2018","unstructured":"Tingwu Wang, Renjie Liao, Jimmy Ba, and Sanja Fidler. 2018. NerveNet: Learning Structured Policy with Graph Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1sqHMZCb"},{"key":"e_1_3_2_1_50_1","volume-title":"An Object-Oriented Representation for Efficient Reinforcement Learning. Ph.,D. Dissertation. Rutgers","author":"Diuk Wasser Carlos Gregorio","unstructured":"Carlos Gregorio Diuk Wasser. 2010. An Object-Oriented Representation for Efficient Reinforcement Learning. Ph.,D. Dissertation. Rutgers, The State University of New Jersey, New Brunswick, New Jersey. A dissertation submitted to the Graduate School-New Brunswick, Rutgers, The State University of New Jersey in partial fulfillment of the requirements for the degree of Doctor of Philosophy, Graduate Program in Computer Science. Written under the direction of Michael L. Littman."},{"key":"e_1_3_2_1_51_1","unstructured":"Clemens Winter. 2023. ragged-buffer version 0.3.7. https:\/\/crates.io\/crates\/ragged-buffer\/0.3.7. Accessed: 2024-03--22."},{"key":"e_1_3_2_1_52_1","unstructured":"Clemens Winter Chris Bamford Costa Huang Th\u00e9o Matricon and Anssi Kanervisto. 2021. RogueNet: Entity Gym compatible ragged batch transformer implementation. https:\/\/github.com\/entity-neural-network\/rogue-net."},{"key":"e_1_3_2_1_53_1","volume-title":"Entity-Based Reinforcement Learning. Clemens' Blog","author":"Winter Clemens","year":"2023","unstructured":"Clemens Winter, Chris Bamford, Costa Huang, Th\u00e9o Matricon, and Anssi Kanervisto. 2023. Entity-Based Reinforcement Learning. Clemens' Blog (2023). https:\/\/clemenswinter.com\/2023\/04\/14\/entity-based-reinforcement-learning\/"},{"key":"e_1_3_2_1_54_1","volume-title":"Entity Gym: Standard interface for entity based reinforcement learning environments. https:\/\/github.com\/entity-neural-network\/entity-gym. Accessed: 2024-02--28.","author":"Winter Clemens","year":"2023","unstructured":"Clemens Winter, Chris Bamford, Costa Huang, Th\u00e9o Matricon, and Anssi Kanervisto. 2023. Entity Gym: Standard interface for entity based reinforcement learning environments. https:\/\/github.com\/entity-neural-network\/entity-gym. Accessed: 2024-02--28."},{"key":"e_1_3_2_1_55_1","unstructured":"Clemens Winter Chris Bamford Costa Huang Th\u00e9o Matricon and Anssi Kanervisto. 2023. Entity Neural Network Trainer: Reinforcement learning training framework for entity-gym environments. https:\/\/github.com\/entity-neural-network\/enn-trainer. Accessed: 2024-07-09."},{"key":"e_1_3_2_1_56_1","volume-title":"Reinforcement Learning for Real Life (RL4RealLife) Workshop at NeurIPS","author":"Wolk Melody","year":"2022","unstructured":"Melody Wolk, Andy Applebaum, Camron Dennler, Patrick Dwyer, Marina Moskowitz, Harold Nguyen, Nicole Nichols, Nicole Park, Paul Rachwalski, Frank Rau,, and Adrian Webster. 2022. Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies. In Reinforcement Learning for Real Life (RL4RealLife) Workshop at NeurIPS 2022. https:\/\/arxiv.org\/abs\/2211.15557"},{"key":"e_1_3_2_1_57_1","volume-title":"Deep Sets. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Zaheer Manzil","year":"2017","unstructured":"Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnab\u00e1s P\u00f3czos, Ruslan Salakhutdinov, and Alexander J. Smola. 2017. Deep Sets. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA. 3391--3401. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/f22e4747da1aa27e363d86d40ff442fe-Abstract.html"},{"key":"e_1_3_2_1_58_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HkxaFoC9KQ","author":"Zambaldi Vinicius","year":"2019","unstructured":"Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, and Peter Battaglia. 2019. Deep reinforcement learning with relational inductive biases. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HkxaFoC9KQ"},{"key":"e_1_3_2_1_59_1","volume-title":"Toward Compositional Generalization in Object-Oriented World Modeling. In International Conference on Machine Learning, ICML 2022","volume":"26864","author":"Zhao Linfeng","year":"2022","unstructured":"Linfeng Zhao, Lingzhi Kong, Robin Walters, and Lawson L. S. Wong. 2022. Toward Compositional Generalization in Object-Oriented World Modeling. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 26841--26864. https:\/\/proceedings.mlr.press\/v162\/zhao22b.html"},{"key":"e_1_3_2_1_60_1","unstructured":"Allan Zhou Vikash Kumar Chelsea Finn and Aravind Rajeswaran. 2022. Policy Architectures for Compositional Generalization in Control. arxiv: 2203.05960 [cs.LG] https:\/\/arxiv.org\/abs\/2203.05960"}],"event":{"name":"CCS '24: ACM SIGSAC Conference on Computer and Communications Security","location":"Salt Lake City UT USA","acronym":"CCS '24","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the Workshop on Autonomous Cybersecurity"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689933.3690835","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689933.3690835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:42:34Z","timestamp":1755974554000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689933.3690835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":60,"alternative-id":["10.1145\/3689933.3690835","10.1145\/3689933"],"URL":"https:\/\/doi.org\/10.1145\/3689933.3690835","relation":{},"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}