{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:32:39Z","timestamp":1782970359880,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"University of Science and Technology of China","award":["WK3490000004"],"award-info":[{"award-number":["WK3490000004"]}]},{"name":"National Nature Science Foundation of China","award":["61836006"],"award-info":[{"award-number":["61836006"]}]},{"name":"National Nature Science Foundation of China","award":["U19B2026"],"award-info":[{"award-number":["U19B2026"]}]},{"name":"National Nature Science Foundation of China","award":["U19B2044"],"award-info":[{"award-number":["U19B2044"]}]},{"name":"National Nature Science Foundation of China","award":["61836011"],"award-info":[{"award-number":["61836011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539391","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"2242-2252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions"],"prefix":"10.1145","author":[{"given":"Rui","family":"Yang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence & University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijie","family":"Geng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuiwang","family":"Ji","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning. In ICLR","author":"Agarwal Rishabh","year":"2021","unstructured":"Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, and Marc G. Bellemare. 2021. Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning. In ICLR 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7476--7484","author":"Ansari Abdul Fatir","year":"2020","unstructured":"Abdul Fatir Ansari, Jonathan Scarlett, and Harold Soh. 2020. A Characteristic Function Approach to Deep Implicit Generative Modeling. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7476--7484."},{"key":"e_1_3_2_1_3_1","volume-title":"Scalable Methods for Computing State Similarity in Deterministic Markov Decision Processes. In The Thirty-Fourth AAAI Conference on Artificial Intelligence. 10069--10076","author":"Castro Pablo Samuel","year":"2020","unstructured":"Pablo Samuel Castro. 2020. Scalable Methods for Computing State Similarity in Deterministic Markov Decision Processes. In The Thirty-Fourth AAAI Conference on Artificial Intelligence. 10069--10076."},{"key":"e_1_3_2_1_4_1","volume-title":"ICML","volume":"97","author":"Du Simon S.","year":"2019","unstructured":"Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dud\u00edk, and John Langford. 2019. Provably efficient RL with Rich Observations via Latent State Decoding. In ICML 2019, Vol. 97. 1665--1674."},{"key":"e_1_3_2_1_5_1","first-page":"1406","article-title":"IMPALA","volume":"2018","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, R\u00e9mi Munos, Karen Simonyan, Volodymyr Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, and Koray Kavukcuoglu. 2018. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. In ICML 2018. 1406--1415.","journal-title":"Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. In ICML"},{"key":"e_1_3_2_1_6_1","volume-title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies. In ICML","volume":"139","author":"Fan Linxi","year":"2021","unstructured":"Linxi Fan, Guanzhi Wang, De-An Huang, Zhiding Yu, Li Fei-Fei, Yuke Zhu, and Animashree Anandkumar. 2021. SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies. In ICML 2021, Vol. 139. 3088--3099."},{"key":"e_1_3_2_1_7_1","volume-title":"Generalization and regularization in DQN. arXiv preprint arXiv:1810.00123","author":"Farebrother Jesse","year":"2018","unstructured":"Jesse Farebrother, Marlos C Machado, and Michael Bowling. 2018. Generalization and regularization in DQN. arXiv preprint arXiv:1810.00123 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Probability and random processes","author":"Grimmett Geoffrey","unstructured":"Geoffrey Grimmett and David Stirzaker. 2020. Probability and random processes. Oxford university press."},{"key":"e_1_3_2_1_9_1","volume-title":"ICML 2018","volume":"80","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 ICML 2018, Vol. 80. 1856--1865."},{"key":"e_1_3_2_1_10_1","volume-title":"ICML","volume":"97","author":"Hafner Danijar","year":"2019","unstructured":"Danijar Hafner, Timothy P. Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, and James Davidson. 2019. Learning Latent Dynamics for Planning from Pixels. In ICML 2019, Vol. 97. 2555--2565."},{"key":"e_1_3_2_1_11_1","volume-title":"ICLR","author":"Hansen Nicklas","year":"2021","unstructured":"Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Aleny\u00e0, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, and Xiaolong Wang. 2021. Self-Supervised Policy Adaptation during Deployment. In ICLR 2021."},{"key":"e_1_3_2_1_12_1","volume-title":"NeurIPS","author":"Igl Maximilian","year":"2019","unstructured":"Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, and Katja Hofmann. 2019. Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck. In NeurIPS 2019."},{"key":"e_1_3_2_1_13_1","volume-title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. CoRR abs\/1806.10293","author":"Kalashnikov Dmitry","year":"2018","unstructured":"Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, and Sergey Levine. 2018. QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. CoRR abs\/1806.10293 (2018)."},{"key":"e_1_3_2_1_14_1","volume-title":"International Joint Conference on Neural Networks.","author":"Lange Sascha","unstructured":"Sascha Lange and Martin A. Riedmiller. 2010. Deep auto-encoder neural networks in reinforcement learning. In International Joint Conference on Neural Networks."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0890-5401(91)90030-6"},{"key":"e_1_3_2_1_17_1","volume-title":"NeurIPS","author":"Laskin Michael","year":"2020","unstructured":"Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, and Aravind Srinivas. 2020. Reinforcement Learning with Augmented Data. In NeurIPS 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning. In ICML","author":"Laskin Michael","year":"2020","unstructured":"Michael Laskin, Aravind Srinivas, and Pieter Abbeel. 2020. CURL: Contrastive Unsupervised Representations for Reinforcement Learning. In ICML 2020."},{"key":"e_1_3_2_1_19_1","volume-title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning. In ICLR","author":"Lee Kimin","year":"2020","unstructured":"Kimin Lee, Kibok Lee, Jinwoo Shin, and Honglak Lee. 2020. Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning. In ICLR 2020."},{"key":"e_1_3_2_1_20_1","volume-title":"Frank","author":"Lehnert Lucas","year":"2020","unstructured":"Lucas Lehnert, Michael L. Littman, and Michael J. Frank. 2020. Reward-predictive representations generalize across tasks in reinforcement learning. PLoS Comput. Biol. 16, 10 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning. CoRR abs\/2006.12862","author":"Raileanu Roberta","year":"2020","unstructured":"Roberta Raileanu, Max Goldstein, Denis Yarats, Ilya Kostrikov, and Rob Fergus. 2020. Automatic Data Augmentation for Generalization in Deep Reinforcement Learning. CoRR abs\/2006.12862 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Kakade","author":"Rajeswaran Aravind","year":"2017","unstructured":"Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, and Sham M. Kakade. 2017. Towards Generalization and Simplicity in Continuous Control. In NeurIPS 2017. 6550--6561."},{"key":"e_1_3_2_1_23_1","volume-title":"Invariant Policy Learning: A Causal Perspective. CoRR abs\/2106.00808","author":"Saengkyongam Sorawit","year":"2021","unstructured":"Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters, and Niklas Pfister. 2021. Invariant Policy Learning: A Causal Perspective. CoRR abs\/2106.00808 (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control","volume":"144","author":"Sonar Anoopkumar","year":"2021","unstructured":"Anoopkumar Sonar, Vincent Pacelli, and Anirudha Majumdar. 2021. Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning. In Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, Vol. 144. 21--33."},{"key":"e_1_3_2_1_25_1","volume-title":"Observational Overfitting in Reinforcement Learning. In ICLR","author":"Song Xingyou","year":"2020","unstructured":"Xingyou Song, Yiding Jiang, Stephen Tu, Yilun Du, and Behnam Neyshabur. 2020. Observational Overfitting in Reinforcement Learning. In ICLR 2020."},{"key":"e_1_3_2_1_26_1","volume-title":"The Distracting Control Suite - A Challenging Benchmark for Reinforcement Learning from Pixels. CoRR abs\/2101.02722","author":"Stone Austin","year":"2021","unstructured":"Austin Stone, Oscar Ramirez, Kurt Konolige, and Rico Jonschkowski. 2021. The Distracting Control Suite - A Challenging Benchmark for Reinforcement Learning from Pixels. CoRR abs\/2101.02722 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"David Budden, Abbas Abdolmaleki, Josh Merel, Andrew Lefrancq, Timothy P. Lillicrap, and Martin A. Riedmiller.","author":"Tassa Yuval","year":"2018","unstructured":"Yuval Tassa, Yotam Doron, Alistair Muldal, Tom Erez, Yazhe Li, Diego de Las Casas, David Budden, Abbas Abdolmaleki, Josh Merel, Andrew Lefrancq, Timothy P. Lillicrap, and Martin A. Riedmiller. 2018. DeepMind Control Suite. CoRR abs\/1801.00690 (2018)."},{"key":"e_1_3_2_1_28_1","volume-title":"Representation Learning with Contrastive Predictive Coding. CoRR abs\/1807.03748","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR abs\/1807.03748 (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic. CoRR abs\/2112.10504","author":"Zhou Qi","year":"2021","unstructured":"ZhihaiWang, JieWang, Qi Zhou, Bin Li, and Houqiang Li. 2021. Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic. CoRR abs\/2112.10504 (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"ICLR","author":"Yarats Denis","year":"2021","unstructured":"Denis Yarats, Ilya Kostrikov, and Rob Fergus. 2021. Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels. In ICLR 2021."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231907"},{"key":"e_1_3_2_1_32_1","volume-title":"Empirical characteristic function estimation and its applications. Econometric reviews 23, 2","author":"Jun Yu.","year":"2004","unstructured":"Jun Yu. 2004. Empirical characteristic function estimation and its applications. Econometric reviews 23, 2 (2004), 93--123."},{"key":"e_1_3_2_1_33_1","volume-title":"Invariant Causal Prediction for Block MDPs. In ICML","volume":"119","author":"Zhang Amy","year":"2020","unstructured":"Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, and Doina Precup. 2020. Invariant Causal Prediction for Block MDPs. In ICML 2020, Vol. 119. 11214--11224."},{"key":"e_1_3_2_1_34_1","volume-title":"ICLR 20211","author":"Zhang Amy","year":"2021","unstructured":"Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, and Sergey Levine. 2021. Learning Invariant Representations for Reinforcement Learning without Reconstruction. In ICLR 20211."},{"key":"e_1_3_2_1_35_1","volume-title":"ICLR","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Ciss\u00e9, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In ICLR 2018."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539391","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:48Z","timestamp":1750186968000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539391"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":35,"alternative-id":["10.1145\/3534678.3539391","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539391","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}