{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T05:17:38Z","timestamp":1735190258820,"version":"3.32.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698641","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T11:38:06Z","timestamp":1731584286000},"page":"81-89","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Inverse Reinforcement Learning for Market Making"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8579-0249","authenticated-orcid":false,"given":"Juraj","family":"Zelman","sequence":"first","affiliation":[{"name":"Richfox Capital, Zurich, Switzerland and Department of Mathematics, ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6923-6662","authenticated-orcid":false,"given":"Martin","family":"Stefanik","sequence":"additional","affiliation":[{"name":"Richfox Capital, Zurich, Switzerland and Department of Mathematics, ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6024-1313","authenticated-orcid":false,"given":"Moritz","family":"Weiss","sequence":"additional","affiliation":[{"name":"Department of Mathematics, ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0125-7484","authenticated-orcid":false,"given":"Josef","family":"Teichmann","sequence":"additional","affiliation":[{"name":"Department of Mathematics, ETH Zurich, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Concrete problems in AI safety. arXiv preprint arXiv:1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697680701381228"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-022-10272-4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC57344.2023.10099211"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/130911196"},{"key":"e_1_3_2_1_6_1","unstructured":"Felix Eigelshoven Andre Ullrich and Douglas Parry. 2021. Cryptocurrency Market Manipulation-A Systematic Literature Review. In ICIS."},{"key":"e_1_3_2_1_7_1","volume-title":"Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248","author":"Fu Justin","year":"2017","unstructured":"Justin Fu, Katie Luo, and Sergey Levine. 2017. Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/math9212689"},{"key":"e_1_3_2_1_9_1","unstructured":"Adam Gleave Mohammad Taufeeque Juan Rocamonde Erik Jenner Steven\u00a0H. Wang Sam Toyer Maximilian Ernestus Nora Belrose Scott Emmons and Stuart Russell. 2022. imitation: Clean Imitation Learning Implementations. arXiv:2211.11972v1 [cs.LG]. arxiv:2211.11972\u00a0[cs.LG]"},{"key":"e_1_3_2_1_10_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2017.1342552"},{"key":"e_1_3_2_1_12_1","volume-title":"Dealing with the inventory risk: a solution to the market making problem. Mathematics and financial economics 7","author":"Gu\u00e9ant Olivier","year":"2013","unstructured":"Olivier Gu\u00e9ant, Charles-Albert Lehalle, and Joaquin Fernandez-Tapia. 2013. Dealing with the inventory risk: a solution to the market making problem. Mathematics and financial economics 7 (2013), 477\u2013507."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861\u20131870."},{"key":"e_1_3_2_1_14_1","volume-title":"Generative adversarial imitation learning. Advances in neural information processing systems 29","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(81)90020-9"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12413"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.finmar.2012.05.004"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria\u00a0Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928\u20131937."},{"key":"e_1_3_2_1_20_1","volume-title":"Efficient training of artificial neural networks for autonomous navigation. Neural computation 3, 1","author":"Pomerleau A","year":"1991","unstructured":"Dean\u00a0A Pomerleau. 1991. Efficient training of artificial neural networks for autonomous navigation. Neural computation 3, 1 (1991), 88\u201397."},{"key":"e_1_3_2_1_21_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 22, 268 (2021), 1\u20138.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627\u2013635","author":"Ross St\u00e9phane","year":"2011","unstructured":"St\u00e9phane Ross, Geoffrey Gordon, and Drew Bagnell. 2011. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627\u2013635."},{"key":"e_1_3_2_1_23_1","volume-title":"Deep reinforcement learning in cryptocurrency market making. arXiv preprint arXiv:1911.08647","author":"Sadighian Jonathan","year":"2019","unstructured":"Jonathan Sadighian. 2019. Deep reinforcement learning in cryptocurrency market making. arXiv preprint arXiv:1911.08647 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Market Making via Reinforcement Learning.(2018). arXiv preprint arXiv:1804.04216","author":"Spooner Tom","year":"2018","unstructured":"Tom Spooner, John Fearnley, Rahul Savani, and Andreas Koukorinis. 2018. Market Making via Reinforcement Learning.(2018). arXiv preprint arXiv:1804.04216 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2018.1489139"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106401"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1142\/S2382626619500114"},{"key":"e_1_3_2_1_29_1","volume-title":"Solana: A new architecture for a high performance blockchain v0. 8.13. Whitepaper","author":"Yakovenko Anatoly","year":"2018","unstructured":"Anatoly Yakovenko. 2018. Solana: A new architecture for a high performance blockchain v0. 8.13. Whitepaper (2018)."},{"volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"Ziebart D","key":"e_1_3_2_1_30_1","unstructured":"Brian\u00a0D Ziebart. 2010. Modeling purposeful adaptive behavior with the principle of maximum causal entropy. Carnegie Mellon University."}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","acronym":"ICAIF '24","location":"Brooklyn NY USA"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T11:40:03Z","timestamp":1735126803000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":30,"alternative-id":["10.1145\/3677052.3698641","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698641","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}