{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:32:55Z","timestamp":1763706775609,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446037","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7570-7574","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Policy Extraction with Neuro-Symbolic Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Rajdeep","family":"Dutta","sequence":"first","affiliation":[{"name":"A*STAR,Institute for Infocomm Research (I2R)"}]},{"given":"Qincheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Ankur","family":"Singh","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research (I2R)"}]},{"given":"Dhruv","family":"Kumarjiguda","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Li","family":"Xiaoli","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research (I2R)"}]},{"given":"Senthilnath","family":"Jayavelu","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research (I2R)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798684"},{"issue":"2017","key":"ref2","first-page":"1","article-title":"Mean Actor Critic","volume":"1050","author":"Asadi","year":"2017","journal-title":"stat"},{"key":"ref3","first-page":"936","article-title":"Neural symbolic regression that scales","volume-title":"International Conference on Machine Learning","author":"Biggio"},{"key":"ref4","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International conference on machine learning","author":"Duan"},{"key":"ref5","first-page":"1","author":"Gao","year":"2022","journal-title":"Scaling Laws for Reward Model Overoptimization"},{"article-title":"Reducing sampling error in the monte carlo policy gradient estimator","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and Multia-gent Systems","author":"Hanna","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.09.007"},{"volume-title":"ReLeaSE (Reinforcement Learning for Structural Evolution)","year":"2018","author":"Isayev","key":"ref8"},{"key":"ref9","article-title":"On a connection between importance sampling and the likelihood ratio policy gradient","volume-title":"Advances in Neural Information Processing Systems","volume":"23","author":"Jie","year":"2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3119000"},{"key":"ref11","first-page":"5979","article-title":"Discovering symbolic policies with deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Landajuela"},{"key":"ref12","first-page":"1","article-title":"Guided policy search","volume-title":"International conference on machine learning","author":"Levine"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aap7885"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094935"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.220097"},{"volume-title":"gplearn: Genetic programming in python","year":"2018","author":"Stephens","key":"ref17"},{"key":"ref18","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in neural information processing systems","volume":"12","author":"Sutton","year":"1999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/wics.56"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aay2631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446037.pdf?arnumber=10446037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:01:43Z","timestamp":1722574903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446037","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}