{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T07:01:36Z","timestamp":1782802896217,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"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":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671595","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"6073-6082","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9656-6193","authenticated-orcid":false,"given":"Yu","family":"Xiong","sequence":"first","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-0816","authenticated-orcid":false,"given":"Zhipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4804-2627","authenticated-orcid":false,"given":"Ye","family":"Huang","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6986-5825","authenticated-orcid":false,"given":"Runze","family":"Wu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-3464","authenticated-orcid":false,"given":"Kai","family":"Guan","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2308-200X","authenticated-orcid":false,"given":"XingChen","family":"Fang","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9632-8400","authenticated-orcid":false,"given":"Ji","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6375-5206","authenticated-orcid":false,"given":"Tianze","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2714-0092","authenticated-orcid":false,"given":"YuJing","family":"Hu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8998-1217","authenticated-orcid":false,"given":"Haoyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-809X","authenticated-orcid":false,"given":"Tangjie","family":"Lyu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5420-0516","authenticated-orcid":false,"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"15784","article-title":"Openxai: Towards a transparent evaluation of model explanations","volume":"35","author":"Agarwal Chirag","year":"2022","unstructured":"Chirag Agarwal, Satyapriya Krishna, Eshika Saxena, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, and Himabindu Lakkaraju. 2022. Openxai: Towards a transparent evaluation of model explanations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 15784--15799.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_2_1","volume-title":"On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049","author":"Alvarez-Melis David","year":"2018","unstructured":"David Alvarez-Melis and Tommi S Jaakkola. 2018. On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049 (2018)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_2_4_1","volume-title":"Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems","author":"Barto Andrew G","year":"2003","unstructured":"Andrew G Barto and Sridhar Mahadevan. 2003. Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems, Vol. 13, 1--2 (2003), 41--77."},{"key":"e_1_3_2_2_5_1","volume-title":"Verifiable reinforcement learning via policy extraction. Advances in neural information processing systems","author":"Bastani Osbert","year":"2018","unstructured":"Osbert Bastani, Yewen Pu, and Armando Solar-Lezama. 2018. Verifiable reinforcement learning via policy extraction. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_6_1","volume-title":"International conference on machine learning. PMLR, 883--892","author":"Chen Jianbo","year":"2018","unstructured":"Jianbo Chen, Le Song, Martin Wainwright, and Michael Jordan. 2018. Learning to explain: An information-theoretic perspective on model interpretation. In International conference on machine learning. PMLR, 883--892."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534159"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359786"},{"key":"e_1_3_2_2_9_1","unstructured":"Gabriel Erion Joseph D Janizek Pascal Sturmfels Scott M Lundberg and Su-In Lee. 2019. Learning explainable models using attribution priors. (2019)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3125739.3125746"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2013.12.007"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"e_1_3_2_2_14_1","volume-title":"International conference on machine learning. PMLR, 1792--1801","author":"Greydanus Samuel","year":"2018","unstructured":"Samuel Greydanus, Anurag Koul, Jonathan Dodge, and Alan Fern. 2018. Visualizing and understanding atari agents. In International conference on machine learning. PMLR, 1792--1801."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.09.007"},{"key":"e_1_3_2_2_17_1","volume-title":"The promise and peril of human evaluation for model interpretability. arXiv preprint arXiv:1711.07414","author":"Herman Bernease","year":"2017","unstructured":"Bernease Herman. 2017. The promise and peril of human evaluation for model interpretability. arXiv preprint arXiv:1711.07414 (2017)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278776"},{"key":"e_1_3_2_2_19_1","volume-title":"Kevin P Murphy, and Chelsea Finn.","author":"Jiang Yiding","year":"2019","unstructured":"Yiding Jiang, Shixiang Shane Gu, Kevin P Murphy, and Chelsea Finn. 2019. Language as an abstraction for hierarchical deep reinforcement learning. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"International conference on machine learning. PMLR, 3110--3119","author":"Jiang Zhengyao","year":"2019","unstructured":"Zhengyao Jiang and Shan Luo. 2019. Neural logic reinforcement learning. In International conference on machine learning. PMLR, 3110--3119."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20663"},{"key":"e_1_3_2_2_22_1","volume-title":"IJCAI\/ECAI Workshop on explainable artificial intelligence.","author":"Juozapaitis Zoe","year":"2019","unstructured":"Zoe Juozapaitis, Anurag Koul, Alan Fern, Martin Erwig, and Finale Doshi-Velez. 2019. Explainable reinforcement learning via reward decomposition. In IJCAI\/ECAI Workshop on explainable artificial intelligence."},{"key":"e_1_3_2_2_23_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v7i1.5280"},{"key":"e_1_3_2_2_25_1","volume-title":"Social attention for autonomous decision-making in dense traffic. arXiv preprint arXiv:1911.12250","author":"Leurent Edouard","year":"2019","unstructured":"Edouard Leurent and Jean Mercat. 2019. Social attention for autonomous decision-making in dense traffic. arXiv preprint arXiv:1911.12250 (2019)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10928-8_25"},{"key":"e_1_3_2_2_27_1","volume-title":"Synthetic benchmarks for scientific research in explainable machine learning. arXiv preprint arXiv:2106.12543","author":"Liu Yang","year":"2021","unstructured":"Yang Liu, Sujay Khandagale, Colin White, and Willie Neiswanger. 2021. Synthetic benchmarks for scientific research in explainable machine learning. arXiv preprint arXiv:2106.12543 (2021)."},{"key":"e_1_3_2_2_28_1","volume-title":"Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888","author":"Lundberg Scott M","year":"2018","unstructured":"Scott M Lundberg, Gabriel G Erion, and Su-In Lee. 2018. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)."},{"key":"e_1_3_2_2_29_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012970"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"e_1_3_2_2_32_1","volume-title":"A survey of explainable reinforcement learning. arXiv preprint arXiv:2202.08434","author":"Milani Stephanie","year":"2022","unstructured":"Stephanie Milani, Nicholay Topin, Manuela Veloso, and Fei Fang. 2022. A survey of explainable reinforcement learning. arXiv preprint arXiv:2202.08434 (2022)."},{"key":"e_1_3_2_2_33_1","first-page":"29529","article-title":"Ella: Exploration through learned language abstraction","volume":"34","author":"Mirchandani Suvir","year":"2021","unstructured":"Suvir Mirchandani, Siddharth Karamcheti, and Dorsa Sadigh. 2021. Ella: Exploration through learned language abstraction. Advances in Neural Information Processing Systems, Vol. 34 (2021), 29529--29540.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_2_35_1","first-page":"9497","article-title":"A boolean task algebra for reinforcement learning","volume":"33","author":"Tasse Geraud Nangue","year":"2020","unstructured":"Geraud Nangue Tasse, Steven James, and Benjamin Rosman. 2020. A boolean task algebra for reinforcement learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9497--9507.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103455"},{"key":"e_1_3_2_2_38_1","volume-title":"Incorporating relational background knowledge into reinforcement learning via differentiable inductive logic programming. arXiv preprint arXiv:2003.10386","author":"Payani Ali","year":"2020","unstructured":"Ali Payani and Faramarz Fekri. 2020. Incorporating relational background knowledge into reinforcement learning via differentiable inductive logic programming. arXiv preprint arXiv:2003.10386 (2020)."},{"key":"e_1_3_2_2_39_1","volume-title":"Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421","author":"Petsiuk Vitali","year":"2018","unstructured":"Vitali Petsiuk, Abir Das, and Kate Saenko. 2018. Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)."},{"key":"e_1_3_2_2_40_1","volume-title":"International cross-domain conference for machine learning and knowledge extraction","author":"Puiutta Erika","unstructured":"Erika Puiutta and Eric MSP Veith. 2020. Explainable reinforcement learning: A survey. In International cross-domain conference for machine learning and knowledge extraction. Springer, 77--95."},{"key":"e_1_3_2_2_41_1","volume-title":"Explain your move: Understanding agent actions using specific and relevant feature attribution. arXiv preprint arXiv:1912.12191","author":"Puri Nikaash","year":"2019","unstructured":"Nikaash Puri, Sukriti Verma, Piyush Gupta, Dhruv Kayastha, Shripad Deshmukh, Balaji Krishnamurthy, and Sameer Singh. 2019. Explain your move: Understanding agent actions using specific and relevant feature attribution. arXiv preprint arXiv:1912.12191 (2019)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"e_1_3_2_2_44_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_2_45_1","volume-title":"International conference on machine learning. PMLR, 3145--3153","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In International conference on machine learning. PMLR, 3145--3153."},{"key":"e_1_3_2_2_46_1","volume-title":"Hierarchical and interpretable skill acquisition in multi-task reinforcement learning. arXiv preprint arXiv:1712.07294","author":"Shu Tianmin","year":"2017","unstructured":"Tianmin Shu, Caiming Xiong, and Richard Socher. 2017. Hierarchical and interpretable skill acquisition in multi-task reinforcement learning. arXiv preprint arXiv:1712.07294 (2017)."},{"key":"e_1_3_2_2_47_1","volume-title":"International Conference on Machine Learning. PMLR, 9767--9779","author":"Sodhani Shagun","year":"2021","unstructured":"Shagun Sodhani, Amy Zhang, and Joelle Pineau. 2021. Multi-task reinforcement learning with context-based representations. In International Conference on Machine Learning. PMLR, 9767--9779."},{"key":"e_1_3_2_2_48_1","volume-title":"International conference on machine learning. PMLR, 3319--3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319--3328."},{"key":"e_1_3_2_2_49_1","first-page":"22574","article-title":"The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning","volume":"34","author":"Tang Yujin","year":"2021","unstructured":"Yujin Tang and David Ha. 2021. The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 22574--22587.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_50_1","volume-title":"Explainable artificial intelligence: a systematic review. arXiv preprint arXiv:2006.00093","author":"Vilone Giulia","year":"2020","unstructured":"Giulia Vilone and Luca Longo. 2020. Explainable artificial intelligence: a systematic review. arXiv preprint arXiv:2006.00093 (2020)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527448"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"e_1_3_2_2_53_1","volume-title":"Singularity hypotheses: A scientific and philosophical assessment","author":"Yampolskiy Roman V","unstructured":"Roman V Yampolskiy and Joshua Fox. 2013. Artificial general intelligence and the human mental model. In Singularity hypotheses: A scientific and philosophical assessment. Springer, 129--145."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10050593"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","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 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671595","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:20Z","timestamp":1750291460000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":56,"alternative-id":["10.1145\/3637528.3671595","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671595","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}