{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:13:15Z","timestamp":1768817595678,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tpami.2024.3469053","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T17:45:57Z","timestamp":1727372757000},"page":"400-412","source":"Crossref","is-referenced-by-count":5,"title":["Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8283-7511","authenticated-orcid":false,"given":"Wenqing","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6298-6464","authenticated-orcid":false,"given":"S. P.","family":"Sharan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8302-7465","authenticated-orcid":false,"given":"Zhiwen","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4673-7975","authenticated-orcid":false,"given":"Kevin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3509-8058","authenticated-orcid":false,"given":"Yihan","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2050-5693","authenticated-orcid":false,"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179268"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798684"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3119000"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v29i1.3554"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012970"},{"key":"ref10","article-title":"Learning symbolic rules for interpretable deep reinforcement learning","author":"Ma","year":"2021"},{"key":"ref11","first-page":"75","article-title":"Combining reinforcement learning with symbolic planning","volume-title":"Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning","author":"Grounds","year":"2005"},{"key":"ref12","article-title":"Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond","author":"Li","year":"2021"},{"key":"ref13","first-page":"5979","article-title":"Discovering symbolic policies with deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Landajuela"},{"key":"ref14","first-page":"5045","article-title":"Programmatically interpretable reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref15","article-title":"Towards deep symbolic reinforcement learning","author":"Garnelo","year":"2016"},{"key":"ref16","first-page":"3505","article-title":"Neuro-symbolic reinforcement learning with first-order logic","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Kimura"},{"key":"ref17","article-title":"Towards symbolic reinforcement learning with common sense","author":"Garcez","year":"2018"},{"key":"ref18","article-title":"Verifiable reinforcement learning via policy extraction","author":"Bastani","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-019-09360-6"},{"key":"ref20","first-page":"1","article-title":"Distilling deep reinforcement learning policies in soft decision trees","volume-title":"Proc. Workshop Explainable Artif. Intell.","author":"Coppens"},{"key":"ref21","article-title":"Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models","author":"Samek","year":"2017"},{"key":"ref22","article-title":"Discovering symbolic models from deep learning with inductive biases","author":"Cranmer","year":"2020"},{"key":"ref23","article-title":"Symbolic learning to optimize: Towards interpretability and scalability","author":"Zheng","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16627"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SBRN.2000.889734"},{"key":"ref26","article-title":"Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning","author":"Garcez","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v43i1.19122"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23889\/suthesis.67068"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aay2631"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1557\/mrc.2019.85"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205539"},{"key":"ref32","first-page":"10684","article-title":"Symbolic distillation for learned TCP congestion control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharan"},{"key":"ref33","article-title":"Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients","author":"Petersen","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ECNN.2000.886220"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554780"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727815"},{"key":"ref37","first-page":"8007","article-title":"Automl-zero: Evolving machine learning algorithms from scratch","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Real"},{"key":"ref38","article-title":"Space: Unsupervised object-oriented scene representation via spatial attention and decomposition","author":"Lin","year":"2020"},{"key":"ref39","article-title":"Gplearn (2015)","author":"Stephens","year":"2019"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","article-title":"Stable baselines3","author":"Raffin","year":"2019"},{"key":"ref42","article-title":"Recurrent PPO from stable baselines","author":"Baselines"},{"key":"ref43","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref45","article-title":"State of the art control of atari games using shallow reinforcement learning","author":"Liang","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref47","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10777928\/10694733.pdf?arnumber=10694733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T06:30:07Z","timestamp":1733380207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10694733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3469053","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}