{"type":"ScholarlyArticle","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","authors":[{"name":"Martin Tappler","slug":"martin-tappler","given":"Martin","family":"Tappler","affiliation":"TU Wien"},{"name":"Ignacio D. Lopez-Miguel","slug":"ignacio-d-lopez-miguel","given":"Ignacio D.","family":"Lopez-Miguel","affiliation":"TU Wien"},{"name":"Sebastian Tschiatschek","slug":"sebastian-tschiatschek","given":"Sebastian","family":"Tschiatschek","affiliation":"University of Vienna"},{"name":"Ezio Bartocci","slug":"ezio-bartocci","given":"Ezio","family":"Bartocci","affiliation":"TU Wien"}],"abstract":"We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-step process, which starts by mining rules from a deep RL policy, constituting a partially symbolic representation.  These rules describe which decisions the RL policy makes and which it avoids making. In the second step, we generalize the mined rules using domain knowledge expressed as metamorphic relations. We adapt these relations from software testing to RL to specify expected changes of actions in response to changes in observations. The third step is evaluating generalized rules to determine which generalizations improve performance when enforced. These improvements show weaknesses in the policy, where it has not learned the general rules and thus can be improved by rule guidance. LEGIBLE supported by metamorphic relations provides a principled way of expressing and enforcing domain knowledge about RL environments. We show the efficacy of our approach by demonstrating that it effectively finds weaknesses, accompanied by explanations of these weaknesses, in eleven RL environments and by showcasing that guiding policy execution with rules improves performance w.r.t. gained reward.","doi":"10.24963/ijcai.2025/696","url":"https://ijcai.org/proceedings/2025/696","pdf":"https://ijcai.org/proceedings/2025/0696.pdf","markdown":"https://ijcai.org/proceedings/2025/696.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/696","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":696,"pages":{"first":6254,"last":6262},"keywords":["Machine Learning: ML: Reinforcement learning","Machine Learning: ML: Explainable/Interpretable machine learning","Multidisciplinary Topics and Applications: MTA: Software engineering","Machine Learning: ML: Trustworthy machine learning"],"videos":[],"references":[{"position":1,"raw":"[Alshiekh et al., 2018] Mohammed Alshiekh, Roderick Bloem, Rüdiger Ehlers, Bettina Könighofer, Scott Niekum, and Ufuk Topcu. Safe reinforcement learning via shielding. In AAAI, pages 2669-2678. AAAI Press, 2018.","title":"Safe reinforcement learning via shielding","authors":"Mohammed Alshiekh, Roderick Bloem, Rüdiger Ehlers, Bettina Könighofer, Scott Niekum, Ufuk Topcu","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Apté and Weiss, 1997] Chidanand Apté and Sholom M. Weiss. Data mining with decision trees and decision rules. Future Gener. Comput. Syst., 13(2-3):197-210, 1997.","title":"Data mining with decision trees and decision rules","authors":"Weiss Apté, Chidanand Apté, Sholom M Weiss","year":"1997","venue":"Future Gener. Comput. Syst","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bastani et al., 2018] Osbert Bastani, Yewen Pu, and Ar- mando Solar-Lezama. Verifiable reinforcement learning via policy extraction. In NeurIPS, pages 2499-2509, 2018.","title":"Verifiable reinforcement learning via policy extraction","authors":"Osbert Bastani, Yewen Pu, Armando Solar-Lezama","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bewley and Lawry, 2021] Tom Bewley and Jonathan Lawry. Tripletree: A versatile interpretable representation of black box agents and their environments. In AAAI, pages 11415-11422. AAAI Press, 2021.","title":"Tripletree: A versatile interpretable representation of black box agents and their environments","authors":"Lawry Bewley, Tom Bewley, Jonathan Lawry","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Biagiola and Tonella, 2024] Matteo Biagiola and Paolo Tonella. Testing of deep reinforcement learning agents with surrogate models. ACM Trans. Softw. Eng. Methodol., 33(3):73:1-73:33, 2024.","title":"Testing of deep reinforcement learning agents with surrogate models","authors":"Tonella Biagiola, Matteo Biagiola, Paolo Tonella","year":"2024","venue":"ACM Trans. Softw. Eng. Methodol","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chandak et al., 2021] Yash Chandak, Scott Niekum, Bruno C. da Silva, Erik G. Learned-Miller, Emma Brunskill, and Philip S. Thomas. Universal off-policy evaluation. In NeurIPS, pages 27475-27490, 2021.","title":"Universal off-policy evaluation","authors":"Yash Chandak, Scott Niekum, C Bruno, Erik G Da Silva, Emma Learned-Miller, Philip S Brunskill, Thomas","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chaslot et al., 2008] Guillaume Chaslot, Sander Bakkes, Istvan Szita, and Pieter Spronck. Monte-carlo tree search: A new framework for game AI. In AIIDE. The AAAI Press, 2008.","title":"Monte-carlo tree search: A new framework for game AI","authors":"Guillaume Chaslot, Sander Bakkes, Istvan Szita, Pieter Spronck","year":"2008","venue":"AIIDE","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2018] Tsong Yueh Chen, Fei-Ching Kuo, Huai Liu, Pak-Lok Poon, Dave Towey, T. H. Tse, and Zhi Quan Zhou. Metamorphic testing: A review of challenges and opportunities. ACM Comput. Surv., 51(1):4:1-4:27, 2018.","title":"Metamorphic testing: A review of challenges and opportunities","authors":"Tsong Yueh, Chen, Fei-Ching Kuo, Huai Liu, Pak-Lok Poon, Dave Towey, T H Tse, Zhi Quan Zhou","year":"2018","venue":"ACM Comput. Surv","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cohen, 1995] William W. Cohen. Fast effective rule induc- tion. In ICML, pages 115-123.","title":"Fast effective rule induction","authors":"William W Cohen","year":null,"venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"Morgan Kaufmann, 1995.","title":null,"authors":"Morgan Kaufmann","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Delfosse et al., 2023] Quentin Delfosse, Hikaru Shindo, Devendra Singh Dhami, and Kristian Kersting. In- terpretable and explainable logical policies via neurally guided symbolic abstraction. In NeurIPS, 2023.","title":"Interpretable and explainable logical policies via neurally guided symbolic abstraction","authors":"Quentin Delfosse, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[DeNero and Klein, 2010] John DeNero and Dan Klein. Teaching introductory artificial intelligence with Pac-Man. Proceedings of the AAAI Conference on Artificial Intelli- gence, 24(3):1885-1889, July 2010.","title":"Teaching introductory artificial intelligence with Pac-Man","authors":"Klein Denero, John Denero, Dan Klein","year":"2010","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dong et al., 2019] Honghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li, and Denny Zhou. Neural logic machines. In ICLR. OpenReview.net, 2019.","title":"Neural logic machines","authors":"Honghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li, Denny Zhou","year":"2019","venue":"ICLR. OpenReview.net","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Dwarakanath et al., 2018] Anurag Dwarakanath, Manish Ahuja, Samarth Sikand, Raghotham M. Rao, R. P. Ja- gadeesh Chandra Bose, Neville Dubash, and Sanjay Pod- der. Identifying implementation bugs in machine learning based image classifiers using metamorphic testing. In IS- STA, pages 118-128. ACM, 2018.","title":"Identifying implementation bugs in machine learning based image classifiers using metamorphic testing","authors":"Anurag Dwarakanath, Manish Ahuja, Samarth Sikand, M Raghotham, R P Rao, Chandra Jagadeesh, Neville Bose, Sanjay Dubash, Podder","year":"2018","venue":"IS-STA","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Falcone, 2010] Yliès Falcone. You should better enforce than verify. In RV, volume 6418 of LNCS, pages 89-105. Springer, 2010.","title":"Yliès Falcone. You should better enforce than verify","authors":"Falcone","year":"2010","venue":"RV","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Giacomo et al., 2020] Giuseppe De Giacomo, Luca Iocchi, Marco Favorito, and Fabio Patrizi. Restraining bolts for reinforcement learning agents. In AAAI, pages 13659- 13662. AAAI Press, 2020.","title":"Restraining bolts for reinforcement learning agents","authors":"Giuseppe De, Giacomo, Luca Iocchi, Marco Favorito, Fabio Patrizi","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Guo and Wei, 2022] Wei Guo and Peng Wei. Explainable deep reinforcement learning for aircraft separation assur- ance. In DASC, pages 1-10, 2022.","title":"Explainable deep reinforcement learning for aircraft separation assurance","authors":"Wei Guo, Peng Wei","year":"2022","venue":"DASC","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Guo et al., 2020] Qianyu Guo, Xiaofei Xie, Yi Li, Xiaoyu Zhang, Yang Liu, Xiaohong Li, and Chao Shen. Audee: Automated testing for deep learning frameworks. In ASE, pages 486-498. IEEE, 2020.","title":"Audee: Automated testing for deep learning frameworks","authors":"Qianyu Guo, Xiaofei Xie, Yi Li, Xiaoyu Zhang, Yang Liu, Xiaohong Li, Chao Shen","year":"2020","venue":"ASE","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hussein et al., 2017] Ahmed Hussein, Mohamed Medhat Gaber, Eyad Elyan, and Chrisina Jayne. Imitation learn- ing: A survey of learning methods. ACM Comput. Surv., 50(2):21:1-21:35, 2017.","title":"Imitation learning: A survey of learning methods","authors":"Ahmed Hussein, Mohamed Medhat Gaber, Eyad Elyan, Chrisina Jayne","year":"2017","venue":"ACM Comput. Surv","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jiang and Li, 2016] Nan Jiang and Lihong Li. Doubly ro- bust off-policy value evaluation for reinforcement learn- ing. In ICML, volume 48 of JMLR Workshop and Confer- ence Proceedings, pages 652-661. JMLR.org, 2016.","title":"Doubly robust off-policy value evaluation for reinforcement learning","authors":"Nan Jiang, Lihong Li","year":"2016","venue":"JMLR Workshop and Conference Proceedings","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Jiang and Luo, 2019] Zhengyao Jiang and Shan Luo. Neu- ral logic reinforcement learning. In ICML, volume 97 of Proceedings of Machine Learning Research, pages 3110- 3119. PMLR, 2019.","title":"Neural logic reinforcement learning","authors":"Luo Jiang, Zhengyao Jiang, Shan Luo","year":"2019","venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Leurent, 2018] Edouard Leurent. An environment for au- tonomous driving decision-making. https://github.com/ eleurent/highway-env, 2018.","title":"Edouard Leurent. An environment for autonomous driving decision-making","authors":"Leurent","year":"2018","venue":null,"doi":null,"url":"https://github.com/eleurent/highway-env,2018","internal_url":null},{"position":23,"raw":"[Li et al., 2023] Zhuo Li, Xiongfei Wu, Derui Zhu, Mingfei Cheng, Siyuan Chen, Fuyuan Zhang, Xiaofei Xie, Lei Ma, and Jianjun Zhao. Generative model-based testing on decision-making policies. In ASE, pages 243-254. IEEE, 2023.","title":"Generative model-based testing on decision-making policies","authors":"Zhuo Li, Xiongfei Wu, Derui Zhu, Mingfei Cheng, Siyuan Chen, Fuyuan Zhang, Xiaofei Xie, Lei Ma, Jianjun Zhao","year":"2023","venue":"ASE","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lundberg and Lee, 2017] Scott M. Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In NeurIPS, pages 4765-4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Marco Tulio Ribeiro et al., 2021] Marco Tulio Ribeiro et al. Python implementation of LIME, 2021. Available at GitHub: https://github.com/marcotcr/lime.","title":"Python implementation of LIME","authors":"Marco Tulio, Ribeiro","year":"2021","venue":null,"doi":null,"url":"https://github.com/marcotcr/lime","internal_url":null},{"position":26,"raw":"[Milani et al., 2022] Stephanie Milani, Zhicheng Zhang, Nicholay Topin, Zheyuan Ryan Shi, Charles A. Kamhoua, Evangelos E. Papalexakis, and Fei Fang. MAVIPER: learning decision tree policies for interpretable multi-agent reinforcement learning. In ECML PKDD, volume 13716 of LNCS, pages 251-266. Springer, 2022.","title":"MAVIPER: learning decision tree policies for interpretable multi-agent reinforcement learning","authors":"Stephanie Milani, Zhicheng Zhang, Nicholay Topin, Zheyuan, Ryan Shi, Charles A Kamhoua, Evangelos E Papalexakis, Fei Fang","year":"2022","venue":"ECML PKDD","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Milani et al., 2024] Stephanie Milani, Nicholay Topin, Manuela Veloso, and Fei Fang. Explainable reinforcement learning: A survey and comparative review. ACM Comput. Surv., 56(7):168:1-168:36, 2024.","title":"Explainable reinforcement learning: A survey and comparative review","authors":"Stephanie Milani, Nicholay Topin, Manuela Veloso, Fei Fang","year":"2024","venue":"ACM Comput. Surv","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Mnih et al., 2015] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Belle- mare, Alex Graves, Martin A. Riedmiller, Andreas Fid- jeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Has- sabis. Human-level control through deep reinforcement learning. Nat., 518(7540):529-533, 2015.","title":"Human-level control through deep reinforcement learning","authors":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin A Riedmiller, Andreas Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis","year":"2015","venue":"Nat","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Molnar, 2022] Christoph Molnar. Interpretable Machine Learning. 2 edition, 2022.","title":"Interpretable Machine Learning","authors":"Christoph Molnar","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Nielsen, 2019] Peter Heine Nielsen. The exciting im- pact of a game changer: When Magnus met AlphaZero, 2019. Appeared in New in Chess and published online at https://www.newinchess.com/media/wysiwyg/product pdf/872.pdf.","title":"The exciting impact of a game changer: When Magnus met AlphaZero","authors":"Peter Heine, Nielsen","year":"2019","venue":"Appeared in New in Chess and","doi":null,"url":"https://www.newinchess.com/media/wysiwyg/productpdf/872.pdf","internal_url":null},{"position":31,"raw":"[Odriozola-Olalde et al., 2023] Haritz Odriozola-Olalde, Maider Zamalloa, and Nestor Arana-Arexolaleiba. Shielded reinforcement learning: A review of reactive methods for safe learning. In SII, pages 1-8. IEEE, 2023.","title":"Haritz Odriozola-Olalde, Maider Zamalloa, and Nestor Arana-Arexolaleiba. Shielded reinforcement learning: A review of reactive methods for safe learning","authors":"Odriozola-Olalde","year":"2023","venue":"SII","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Oriol Vinyals et al., 2019] Oriol Vinyals et al. Grandmaster level in StarCraft II using multi-agent reinforcement learn- ing. Nat., 575(7782):350-354, 2019.","title":"Oriol Vinyals et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning","authors":"Oriol Vinyals","year":"2019","venue":"Nat","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Raffin et al., 2021] Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. Stable-baselines3: Reliable reinforcement learning implementations. Journal of Machine Learning Research, 22(268):1-8, 2021.","title":"Stable-baselines3: Reliable reinforcement learning implementations","authors":"Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, Noah Dormann","year":"2021","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Ribeiro et al., 2016] Marco Túlio Ribeiro, Sameer Singh, and Carlos Guestrin. \"Why should I trust you?\": Explain- ing the predictions of any classifier. In SIGKDD, pages 1135-1144. ACM, 2016.","title":"Why should I trust you?\": Explaining the predictions of any classifier","authors":"Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Silver et al., 2016] David Silver, Aja Huang, Chris J. Mad- dison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Ve- davyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P. Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hassabis. Mas- tering the game of Go with deep neural networks and tree search. Nat., 529(7587):484-489, 2016.","title":"Mastering the game of Go with deep neural networks and tree search","authors":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Vedavyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis","year":"2016","venue":"Nat","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Silver et al., 2018] David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, and Demis Hassabis. A general reinforcement learning algo- rithm that masters chess, shogi, and Go through self-play. Science, 362(6419):1140-1144, 2018.","title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play","authors":"David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis","year":"2018","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Tappler et al., 2022] Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig, and Bettina Könighofer. Search- based testing of reinforcement learning. In IJCAI, pages 503-510. ijcai.org, 2022.","title":"Searchbased testing of reinforcement learning","authors":"Martin Tappler, Filip Cano Córdoba, Bernhard K Aichernig, Bettina Könighofer","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Tappler et al., 2024a] Martin Tappler, Edi Muskardin, Bern- hard K. Aichernig, and Bettina Könighofer. Learning en- vironment models with continuous stochastic dynamics - with an application to deep RL testing. In IEEE Con- ference on Software Testing, Verification and Validation, ICST 2024, pages 197-208. IEEE, 2024.","title":"Learning environment models with continuous stochastic dynamicswith an application to deep RL testing","authors":"Tappler","year":"2024","venue":"IEEE Conference on Software Testing, Verification and Validation, ICST 2024","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Tappler et al., 2024b] Martin Tappler, Andrea Pferscher, Bernhard K. Aichernig, and Bettina Könighofer. Learning and repair of deep reinforcement learning policies from fuzz-testing data. In ICSE, pages 6:1-6:13. ACM, 2024.","title":"Learning and repair of deep reinforcement learning policies from fuzz-testing data","authors":"Tappler","year":"2024","venue":"ICSE","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Torrey and Shavlik, 2010] Lisa Torrey and Jude Shavlik. Transfer learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pages 242-264. IGI Global, 2010.","title":"Transfer learning","authors":"Torrey, Shavlik, Lisa Torrey, Jude Shavlik","year":"2010","venue":"Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Towers et al., 2024] Mark Towers, Ariel Kwiatkowski, Jor- dan Terry, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, Arjun KG, Rodrigo Perez-Vicente, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, and Omar G. Younis. Gymnasium: A standard interface for reinforcement learn- ing environments, 2024.","title":"Gymnasium: A standard interface for reinforcement learning environments","authors":"Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U Balis, Gianluca De Cola, Tristan Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, K G Arjun, Rodrigo Perez-Vicente, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G Younis","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Uehara et al., 2022] Masatoshi Uehara, Chengchun Shi, and Nathan Kallus. A review of off-policy evaluation in reinforcement learning. CoRR, abs/2212.06355, 2022.","title":"A review of off-policy evaluation in reinforcement learning","authors":"Masatoshi Uehara, Chengchun Shi, Nathan Kallus","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[van Hasselt et al., 2016] Hado van Hasselt, Arthur Guez, and David Silver. Deep reinforcement learning with dou- ble Q-learning. In AAAI, pages 2094-2100. AAAI Press, 2016.","title":"Deep reinforcement learning with double Q-learning","authors":"Van Hasselt","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Watkins and Dayan, 1992] Christopher J. C. H. Watkins and Peter Dayan. Technical note Q-learning. Mach. Learn., 8:279-292, 1992.","title":"Technical note Q-learning","authors":"J C H Christopher, Peter Watkins, Dayan","year":"1992","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Welch, 1947] B. L. Welch. The generalization of 'student's' problem when several different population variances are involved. Biometrika, 34(1/2):28-35, 1947.","title":"The generalization of 'student's' problem when several different population variances are involved","authors":"B L Welch","year":"1947","venue":"Biometrika","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Xie et al., 2011] Xiaoyuan Xie, Joshua Wing Kei Ho, Chris- tian Murphy, Gail E. Kaiser, Baowen Xu, and Tsong Yueh Chen. Testing and validating machine learning classifiers by metamorphic testing. J. Syst. Softw., 84(4):544-558, 2011.","title":"Testing and validating machine learning classifiers by metamorphic testing","authors":"Xiaoyuan Xie, Joshua Wing Kei, Christian Ho, Gail E Murphy, Baowen Kaiser, Tsong Xu, Chen Yueh","year":"2011","venue":"J. Syst. Softw","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zambaldi et al., 2018] Vinícius Flores Zambaldi, David Ra- poso, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M. Botvinick, Oriol Vinyals, and Peter W. Battaglia. Relational deep reinforce- ment learning. CoRR, abs/1806.01830, 2018.","title":"Relational deep reinforcement learning","authors":"Vinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P Reichert, Timothy P Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M Botvinick, Oriol Vinyals, Peter W Battaglia","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhang et al., 2022] Jie M. Zhang, Mark Harman, Lei Ma, and Yang Liu. Machine learning testing: Survey, land- scapes and horizons. IEEE Trans. Software Eng., 48(2):1- 36, 2022.","title":"Machine learning testing: Survey, landscapes and horizons","authors":"M Jie, Mark Zhang, Lei Harman, Yang Ma, Liu","year":"2022","venue":"IEEE Trans. Software Eng","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Zolfagharian et al., 2023] Amirhossein Zolfaghar- ian, Manel Abdellatif, Lionel C. Briand, Mojtaba Bagherzadeh, and Ramesh S. A search-based testing approach for deep reinforcement learning agents. IEEE Trans. Software Eng., 49(7):3715-3735, 2023.","title":"A search-based testing approach for deep reinforcement learning agents","authors":"Zolfagharian","year":"2023","venue":"IEEE Trans. Software Eng","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}