{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:22:56Z","timestamp":1771698176389,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599856","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"4003-4012","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7882-8698","authenticated-orcid":false,"given":"Yuchen","family":"Fang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5701-4832","authenticated-orcid":false,"given":"Zhenggang","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4032-9615","authenticated-orcid":false,"given":"Kan","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1951-2594","authenticated-orcid":false,"given":"Weiqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5095-3377","authenticated-orcid":false,"given":"Li","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9472-600X","authenticated-orcid":false,"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-8442","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2425","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0476-8020","authenticated-orcid":false,"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330647"},{"key":"e_1_3_2_2_2_1","volume-title":"?Reinforcementlearning based portfolio management with augmented asset movement prediction states,\" in AAAI","author":"Ye Y.","year":"2020","unstructured":"Y. Ye , H. Pei , B. Wang , P.-Y. Chen , Y. Zhu , J. Xiao , and B. Li , ?Reinforcementlearning based portfolio management with augmented asset movement prediction states,\" in AAAI , 2020 . Y. Ye, H. Pei, B. Wang, P.-Y. Chen, Y. Zhu, J. Xiao, and B. Li, ?Reinforcementlearning based portfolio management with augmented asset movement prediction states,\" in AAAI, 2020."},{"key":"e_1_3_2_2_3_1","volume-title":"?Optimal execution with limit and market orders,\" Quantitative Finance","author":"Cartea A.","unstructured":"A. Cartea and S. Jaimungal , ?Optimal execution with limit and market orders,\" Quantitative Finance , vol. 15 , no. 8, pp. 1279--1291, 2015. A. Cartea and S. Jaimungal, ?Optimal execution with limit and market orders,\" Quantitative Finance, vol. 15, no. 8, pp. 1279--1291, 2015."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Y. Fang K. Ren W. Liu D. Zhou W. Zhang J. Bian Y. Yu and T.-Y. Liu ?Universal trading for order execution with oracle policy distillation \" in AAAI 2021. Y. Fang K. Ren W. Liu D. Zhou W. Zhang J. Bian Y. Yu and T.-Y. Liu ?Universal trading for order execution with oracle policy distillation \" in AAAI 2021.","DOI":"10.1609\/aaai.v35i1.16083"},{"key":"e_1_3_2_2_5_1","volume-title":"?Optimal execution of portfolio transactions,\" Journal of Risk","author":"Almgren R.","year":"2001","unstructured":"R. Almgren and N. Chriss , ?Optimal execution of portfolio transactions,\" Journal of Risk , 2001 . R. Almgren and N. Chriss, ?Optimal execution of portfolio transactions,\" Journal of Risk, 2001."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1145\/988772.988801","volume-title":"?Competitive algorithms for vwap and limit order trading,\" in Proceedings of the 5th ACM conference on Electronic commerce","author":"Kakade S. M.","year":"2004","unstructured":"S. M. Kakade , M. Kearns , Y. Mansour , and L. E. Ortiz , ?Competitive algorithms for vwap and limit order trading,\" in Proceedings of the 5th ACM conference on Electronic commerce , 2004 , pp. 189 -- 198 . S. M. Kakade, M. Kearns, Y. Mansour, and L. E. Ortiz, ?Competitive algorithms for vwap and limit order trading,\" in Proceedings of the 5th ACM conference on Electronic commerce, 2004, pp. 189--198."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2007.904825"},{"key":"e_1_3_2_2_8_1","volume-title":"Double deep q-learning for optimal execution,\" CoRR","author":"Ning B.","year":"2018","unstructured":"B. Ning , F. H. T. Ling , and S. Jaimungal , \" Double deep q-learning for optimal execution,\" CoRR , 2018 . B. Ning, F. H. T. Ling, and S. Jaimungal, \"Double deep q-learning for optimal execution,\" CoRR, 2018."},{"key":"e_1_3_2_2_9_1","volume-title":"An end-to-end optimal trade execution framework based on proximal policy optimization,\" in IJCAI","author":"Lin S.","year":"2020","unstructured":"S. Lin and P. A. Beling , \" An end-to-end optimal trade execution framework based on proximal policy optimization,\" in IJCAI , 2020 . S. Lin and P. A. Beling, \"An end-to-end optimal trade execution framework based on proximal policy optimization,\" in IJCAI, 2020."},{"key":"e_1_3_2_2_10_1","first-page":"1","article-title":"Factorized q-learning for large-scale multi-agent systems","author":"Zhou M.","year":"2019","unstructured":"M. Zhou , Y. Chen , Y. Wen , Y. Yang , Y. Su , W. Zhang , D. Zhang , and J. Wang , \" Factorized q-learning for large-scale multi-agent systems ,\" in Proceedings of the First International Conference on Distributed Artificial Intelligence , 2019 , pp. 1 -- 7 . M. Zhou, Y. Chen, Y. Wen, Y. Yang, Y. Su, W. Zhang, D. Zhang, and J. Wang, \"Factorized q-learning for large-scale multi-agent systems,\" in Proceedings of the First International Conference on Distributed Artificial Intelligence, 2019, pp. 1--7.","journal-title":"Proceedings of the First International Conference on Distributed Artificial Intelligence"},{"key":"e_1_3_2_2_11_1","volume-title":"Independent vs. cooperative agents,\" in ICML","author":"Tan M.","year":"1993","unstructured":"M. Tan , \"Multi-agent reinforcement learning : Independent vs. cooperative agents,\" in ICML , 1993 . M. Tan, \"Multi-agent reinforcement learning: Independent vs. cooperative agents,\" in ICML, 1993."},{"key":"e_1_3_2_2_12_1","first-page":"980","article-title":"A cooperative multi-agent reinforcement learning framework for resource balancing in complex logistics network,\" in Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","author":"Li X.","year":"2019","unstructured":"X. Li , J. Zhang , J. Bian , Y. Tong , and T.-Y. Liu , \" A cooperative multi-agent reinforcement learning framework for resource balancing in complex logistics network,\" in Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems . International Foundation for Autonomous Agents and Multiagent Systems , 2019 , pp. 980 -- 988 . X. Li, J. Zhang, J. Bian, Y. Tong, and T.-Y. Liu, \"A cooperative multi-agent reinforcement learning framework for resource balancing in complex logistics network,\" in Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 2019, pp. 980--988.","journal-title":"International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"e_1_3_2_2_13_1","volume-title":"Counterfactual multi-agent policy gradients,\" in Proceedings of the AAAI Conference on Artificial Intelligence","author":"Foerster J.","year":"2018","unstructured":"J. Foerster , G. Farquhar , T. Afouras , N. Nardelli , and S. Whiteson , \" Counterfactual multi-agent policy gradients,\" in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 32 , 2018 . J. Foerster, G. Farquhar, T. Afouras, N. Nardelli, and S. Whiteson, \"Counterfactual multi-agent policy gradients,\" in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, 2018."},{"key":"e_1_3_2_2_14_1","first-page":"5872","volume-title":"PMLR","author":"Zhang K.","year":"2018","unstructured":"K. Zhang , Z. Yang , H. Liu , T. Zhang , and T. Basar , \" Fully decentralized multi-agent reinforcement learning with networked agents,\" in International Conference on Machine Learning . PMLR , 2018 , pp. 5872 -- 5881 . K. Zhang, Z. Yang, H. Liu, T. Zhang, and T. Basar, \"Fully decentralized multi-agent reinforcement learning with networked agents,\" in International Conference on Machine Learning. PMLR, 2018, pp. 5872--5881."},{"key":"e_1_3_2_2_15_1","article-title":"Hierarchical multiagent reinforcement learning for allocating guaranteed display ads","author":"Wang L.","year":"2021","unstructured":"L. Wang , L. Han , X. Chen , C. Li , J. Huang , W. Zhang , W. Zhang , X. He , and D. Luo , \" Hierarchical multiagent reinforcement learning for allocating guaranteed display ads ,\" IEEE Transactions on Neural Networks and Learning Systems , 2021 . L.Wang, L. Han, X. Chen, C. Li, J. Huang,W. Zhang,W. Zhang, X. He, and D. Luo, \"Hierarchical multiagent reinforcement learning for allocating guaranteed display ads,\" IEEE Transactions on Neural Networks and Learning Systems, 2021.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_2_16_1","volume-title":"Tarmac: Targeted multi-agent communication,\" in International Conference on Machine Learning","author":"Das A.","year":"2019","unstructured":"A. Das , T. Gervet , J. Romoff , D. Batra , D. Parikh , M. Rabbat , and J. Pineau , \" Tarmac: Targeted multi-agent communication,\" in International Conference on Machine Learning , 2019 . A. Das, T. Gervet, J. Romoff, D. Batra, D. Parikh, M. Rabbat, and J. Pineau, \"Tarmac: Targeted multi-agent communication,\" in International Conference on Machine Learning, 2019."},{"key":"e_1_3_2_2_17_1","volume-title":"Fergus et al., \"Learning multiagent communication with backpropagation,\" NeurIPS","author":"Sukhbaatar S.","year":"2016","unstructured":"S. Sukhbaatar , R. Fergus et al., \"Learning multiagent communication with backpropagation,\" NeurIPS , 2016 . S. Sukhbaatar, R. Fergus et al., \"Learning multiagent communication with backpropagation,\" NeurIPS, 2016."},{"key":"e_1_3_2_2_18_1","volume-title":"Lu et al., \"Learning individually inferred communication for multiagent cooperation,\" NeurIPS","author":"Huang T.","year":"2020","unstructured":"T. Huang , Z. Lu et al., \"Learning individually inferred communication for multiagent cooperation,\" NeurIPS , 2020 . T. Huang, Z. Lu et al., \"Learning individually inferred communication for multiagent cooperation,\" NeurIPS, 2020."},{"key":"e_1_3_2_2_19_1","volume-title":"Communication in multi-agent reinforcement learning: Intention sharing,\" in ICLR","author":"Kim W.","year":"2020","unstructured":"W. Kim , J. Park , and Y. Sung , \" Communication in multi-agent reinforcement learning: Intention sharing,\" in ICLR , 2020 . W. Kim, J. Park, and Y. Sung, \"Communication in multi-agent reinforcement learning: Intention sharing,\" in ICLR, 2020."},{"key":"e_1_3_2_2_20_1","volume-title":"Intention is choice with commitment,\" Artificial intelligence","author":"Cohen P. R.","year":"1990","unstructured":"P. R. Cohen and H. J. Levesque , \" Intention is choice with commitment,\" Artificial intelligence , 1990 . P. R. Cohen and H. J. Levesque, \"Intention is choice with commitment,\" Artificial intelligence, 1990."},{"key":"e_1_3_2_2_21_1","volume-title":"Understanding and sharing intentions: The origins of cultural cognition,\" Behavioral and brain sciences","author":"Tomasello M.","year":"2005","unstructured":"M. Tomasello , M. Carpenter , J. Call , T. Behne , and H. Moll , \" Understanding and sharing intentions: The origins of cultural cognition,\" Behavioral and brain sciences , 2005 . M. Tomasello, M. Carpenter, J. Call, T. Behne, and H. Moll, \"Understanding and sharing intentions: The origins of cultural cognition,\" Behavioral and brain sciences, 2005."},{"key":"e_1_3_2_2_22_1","volume-title":"A reinforcement learning extension to the almgrenchriss framework for optimal trade execution,\" in CIFEr","author":"Hendricks D.","year":"2014","unstructured":"D. Hendricks and D. Wilcox , \" A reinforcement learning extension to the almgrenchriss framework for optimal trade execution,\" in CIFEr , 2014 . D. Hendricks and D. Wilcox, \"A reinforcement learning extension to the almgrenchriss framework for optimal trade execution,\" in CIFEr, 2014."},{"key":"e_1_3_2_2_23_1","unstructured":"R. Hu \"Optimal order execution using stochastic control and reinforcement learning \" 2016. R. Hu \"Optimal order execution using stochastic control and reinforcement learning \" 2016."},{"key":"e_1_3_2_2_24_1","first-page":"3374766","article-title":"Deep execution-value and policy based reinforcement learning for trading and beating market benchmarks","author":"Dab\u00e9rius K.","year":"2019","unstructured":"K. Dab\u00e9rius , E. Granat , and P. Karlsson , \" Deep execution-value and policy based reinforcement learning for trading and beating market benchmarks ,\" Available at SSRN 3374766 , 2019 . K. Dab\u00e9rius, E. Granat, and P. Karlsson, \"Deep execution-value and policy based reinforcement learning for trading and beating market benchmarks,\" Available at SSRN 3374766, 2019.","journal-title":"Available at SSRN"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(97)00012-8"},{"key":"e_1_3_2_2_26_1","volume-title":"Reinforcement learning for optimized trade execution,\" in ICML","author":"Nevmyvaka Y.","year":"2006","unstructured":"Y. Nevmyvaka , Y. Feng , and M. Kearns , \" Reinforcement learning for optimized trade execution,\" in ICML , 2006 . Y. Nevmyvaka, Y. Feng, and M. Kearns, \"Reinforcement learning for optimized trade execution,\" in ICML, 2006."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"e_1_3_2_2_28_1","unstructured":"W. Bao and X.-y. Liu \"Multi-agent deep reinforcement learning for liquidation strategy analysis \" CoRR 2019. W. Bao and X.-y. Liu \"Multi-agent deep reinforcement learning for liquidation strategy analysis \" CoRR 2019."},{"key":"e_1_3_2_2_29_1","volume-title":"Multi-agent reinforcement learning in a realistic limit order book market simulation,\" Proceedings of the First ACM International Conference on AI in Finance","author":"Karpe M.","year":"2020","unstructured":"M. Karpe , J. Fang , Z. Ma , and C. Wang , \" Multi-agent reinforcement learning in a realistic limit order book market simulation,\" Proceedings of the First ACM International Conference on AI in Finance , 2020 . M. Karpe, J. Fang, Z. Ma, and C. Wang, \"Multi-agent reinforcement learning in a realistic limit order book market simulation,\" Proceedings of the First ACM International Conference on AI in Finance, 2020."},{"key":"e_1_3_2_2_30_1","volume-title":"Modelling stock markets by multi-agent reinforcement learning,\" Computational Economics","author":"Lussange J.","year":"2021","unstructured":"J. Lussange , I. Lazarevich , S. Bourgeois-Gironde , S. Palminteri , and B. Gutkin , \" Modelling stock markets by multi-agent reinforcement learning,\" Computational Economics , 2021 . J. Lussange, I. Lazarevich, S. Bourgeois-Gironde, S. Palminteri, and B. Gutkin, \"Modelling stock markets by multi-agent reinforcement learning,\" Computational Economics, 2021."},{"key":"e_1_3_2_2_31_1","volume-title":"Stock market microstructure inference via multi-agent reinforcement learning,\" CoRR","author":"Lussange J.","year":"2019","unstructured":"J. Lussange , I. Lazarevich , S. Bourgeois Gironde , S. Palminteri , and B. Gutkin , \" Stock market microstructure inference via multi-agent reinforcement learning,\" CoRR , 2019 . J. Lussange, I. Lazarevich, S. Bourgeois Gironde, S. Palminteri, and B. Gutkin, \"Stock market microstructure inference via multi-agent reinforcement learning,\" CoRR, 2019."},{"key":"e_1_3_2_2_32_1","volume-title":"Maps: Multi-agent reinforcement learningbased portfolio management system,\" in IJCAI","author":"Lee J.","year":"2020","unstructured":"J. Lee , R. Kim , S.-W. Yi , and J. Kang , \" Maps: Multi-agent reinforcement learningbased portfolio management system,\" in IJCAI , 2020 . J. Lee, R. Kim, S.-W. Yi, and J. Kang, \"Maps: Multi-agent reinforcement learningbased portfolio management system,\" in IJCAI, 2020."},{"key":"e_1_3_2_2_33_1","volume-title":"Commission fee is not enough: A hierarchical reinforced framework for portfolio management,\" in AAAI","author":"Wang R.","year":"2021","unstructured":"R. Wang , H. Wei , B. An , Z. Feng , and J. Yao , \" Commission fee is not enough: A hierarchical reinforced framework for portfolio management,\" in AAAI , 2021 . R. Wang, H. Wei, B. An, Z. Feng, and J. Yao, \"Commission fee is not enough: A hierarchical reinforced framework for portfolio management,\" in AAAI, 2021."},{"key":"e_1_3_2_2_34_1","volume-title":"Querypomdp: Pomdp-based communication in multiagent systems,\" in European Workshop on Multi-Agent Systems","author":"Melo F. S.","year":"2011","unstructured":"F. S. Melo , M. T. Spaan , and S. J. Witwicki , \" Querypomdp: Pomdp-based communication in multiagent systems,\" in European Workshop on Multi-Agent Systems , 2011 . F. S. Melo, M. T. Spaan, and S. J. Witwicki, \"Querypomdp: Pomdp-based communication in multiagent systems,\" in European Workshop on Multi-Agent Systems, 2011."},{"key":"e_1_3_2_2_35_1","volume-title":"Cooperative multi-agent learning: The state of the art,\" Autonomous agents and multi-agent systems","author":"Panait L.","year":"2005","unstructured":"L. Panait and S. Luke , \" Cooperative multi-agent learning: The state of the art,\" Autonomous agents and multi-agent systems , 2005 . L. Panait and S. Luke, \"Cooperative multi-agent learning: The state of the art,\" Autonomous agents and multi-agent systems, 2005."},{"key":"e_1_3_2_2_36_1","volume-title":"Learning to communicate with deep multi-agent reinforcement learning,\" NeurIPS","author":"Foerster J.","year":"2016","unstructured":"J. Foerster , I. A. Assael , N. De Freitas , and S. Whiteson , \" Learning to communicate with deep multi-agent reinforcement learning,\" NeurIPS , 2016 . J. Foerster, I. A. Assael, N. De Freitas, and S. Whiteson, \"Learning to communicate with deep multi-agent reinforcement learning,\" NeurIPS, 2016."},{"key":"e_1_3_2_2_37_1","volume-title":"Graph convolutional reinforcement learning,\" in ICLR","author":"Jiang J.","year":"2020","unstructured":"J. Jiang , C. Dun , T. Huang , and Z. Lu , \" Graph convolutional reinforcement learning,\" in ICLR , 2020 . J. Jiang, C. Dun, T. Huang, and Z. Lu, \"Graph convolutional reinforcement learning,\" in ICLR, 2020."},{"key":"e_1_3_2_2_38_1","volume-title":"Learning attentional communication for multi-agent cooperation,\" NeurIPS","author":"Jiang J.","year":"2018","unstructured":"J. Jiang and Z. Lu , \" Learning attentional communication for multi-agent cooperation,\" NeurIPS , 2018 . J. Jiang and Z. Lu, \"Learning attentional communication for multi-agent cooperation,\" NeurIPS, 2018."},{"key":"e_1_3_2_2_39_1","volume-title":"Learning to schedule communication in multi-agent reinforcement learning,\" ICLR","author":"Kim D.","year":"2019","unstructured":"D. Kim , S. Moon , D. Hostallero , W. J. Kang , T. Lee , K. Son , and Y. Yi , \" Learning to schedule communication in multi-agent reinforcement learning,\" ICLR , 2019 . D. Kim, S. Moon, D. Hostallero, W. J. Kang, T. Lee, K. Son, and Y. Yi, \"Learning to schedule communication in multi-agent reinforcement learning,\" ICLR, 2019."},{"key":"e_1_3_2_2_40_1","volume-title":"Emergence of human-level coordination in learning to play starcraft combat games,\" CoRR","author":"Peng P.","year":"2017","unstructured":"P. Peng , Y. Wen , Y. Yang , Q. Yuan , Z. Tang , and et. al., \" Multiagent bidirectionallycoordinated nets : Emergence of human-level coordination in learning to play starcraft combat games,\" CoRR , 2017 . P. Peng, Y.Wen, Y. Yang, Q. Yuan, Z. Tang, and et. al., \"Multiagent bidirectionallycoordinated nets: Emergence of human-level coordination in learning to play starcraft combat games,\" CoRR, 2017."},{"key":"e_1_3_2_2_41_1","volume-title":"PMLR","author":"Rabinowitz N.","year":"2018","unstructured":"N. Rabinowitz , F. Perbet , F. Song , C. Zhang , S. A. Eslami , and M. Botvinick , \" Machine theory of mind,\" in International conference onmachine learning . PMLR , 2018 . N. Rabinowitz, F. Perbet, F. Song, C. Zhang, S. A. Eslami, and M. Botvinick, \"Machine theory of mind,\" in International conference onmachine learning. PMLR, 2018."},{"key":"e_1_3_2_2_42_1","volume-title":"Modeling others using oneself in multi-agent reinforcement learning,\" in ICML","author":"Raileanu R.","year":"2018","unstructured":"R. Raileanu , E. Denton , A. Szlam , and R. Fergus , \" Modeling others using oneself in multi-agent reinforcement learning,\" in ICML , 2018 . R. Raileanu, E. Denton, A. Szlam, and R. Fergus, \"Modeling others using oneself in multi-agent reinforcement learning,\" in ICML, 2018."},{"key":"e_1_3_2_2_43_1","volume-title":"Multiagent actor-critic for mixed cooperative-competitive environments,\" NeurIPS","author":"Lowe R.","year":"2017","unstructured":"R. Lowe , Y. I. Wu , A. Tamar , J. Harb , O. Pieter Abbeel , and I. Mordatch , \" Multiagent actor-critic for mixed cooperative-competitive environments,\" NeurIPS , 2017 . R. Lowe, Y. I. Wu, A. Tamar, J. Harb, O. Pieter Abbeel, and I. Mordatch, \"Multiagent actor-critic for mixed cooperative-competitive environments,\" NeurIPS, 2017."},{"key":"e_1_3_2_2_44_1","volume-title":"Algorithmic and high-frequency trading","author":"Jaimungal S.","year":"2015","unstructured":"\u00c1. Cartea, S. Jaimungal , and J. Penalva , Algorithmic and high-frequency trading . Cambridge University Press , 2015 . \u00c1. Cartea, S. Jaimungal, and J. Penalva, Algorithmic and high-frequency trading. Cambridge University Press, 2015."},{"key":"e_1_3_2_2_45_1","volume-title":"Proximal policy optimization algorithms,\" CoRR","author":"Schulman J.","year":"2017","unstructured":"J. Schulman , F. Wolski , P. Dhariwal , A. Radford , and O. Klimov , \" Proximal policy optimization algorithms,\" CoRR , 2017 . J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, \"Proximal policy optimization algorithms,\" CoRR, 2017."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1993.tb04702.x"},{"key":"e_1_3_2_2_47_1","volume-title":"An ai-oriented quantitative investment platform,\" CoRR","author":"Yang X.","year":"2020","unstructured":"X. Yang , W. Liu , D. Zhou , J. Bian , and T.-Y. Liu , \"Qlib : An ai-oriented quantitative investment platform,\" CoRR , 2020 . X. Yang, W. Liu, D. Zhou, J. Bian, and T.-Y. Liu, \"Qlib: An ai-oriented quantitative investment platform,\" CoRR, 2020."},{"key":"e_1_3_2_2_48_1","volume-title":"Median of the","author":"Bhattacharya B.","year":"2002","unstructured":"B. Bhattacharya and D. Habtzghi , \" Median of the p value under the alternative hypothesis,\" The American Statistician , 2002 . B. Bhattacharya and D. Habtzghi, \"Median of the p value under the alternative hypothesis,\" The American Statistician, 2002."},{"key":"e_1_3_2_2_49_1","volume-title":"Learning phrase representations using rnn encoder--decoder for statistical machine translation,\" in EMNLP","author":"Cho K.","year":"2014","unstructured":"K. Cho , B. van Merrienboer , C. Gulcehre , D. Bahdanau , F. Bougares , H. Schwenk , and Y. Bengio , \" Learning phrase representations using rnn encoder--decoder for statistical machine translation,\" in EMNLP , 2014 . K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, \"Learning phrase representations using rnn encoder--decoder for statistical machine translation,\" in EMNLP, 2014."},{"key":"e_1_3_2_2_50_1","volume-title":"Attention is all you need,\" NeurIPS","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani , N. Shazeer , N. Parmar , J. Uszkoreit , L. Jones , A. N. Gomez , L. Kaiser , and I. Polosukhin , \" Attention is all you need,\" NeurIPS , 2017 . A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, \"Attention is all you need,\" NeurIPS, 2017."}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599856","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:23Z","timestamp":1750182563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":50,"alternative-id":["10.1145\/3580305.3599856","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599856","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}