{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:00:13Z","timestamp":1775066413251,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811660","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"448-454","source":"Crossref","is-referenced-by-count":6,"title":["OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching"],"prefix":"10.1109","author":[{"given":"Hana","family":"Hoshino","sequence":"first","affiliation":[{"name":"School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Ota","sequence":"additional","affiliation":[{"name":"School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asako","family":"Kanezaki","sequence":"additional","affiliation":[{"name":"School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rio","family":"Yokota","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Global Scientific Information and Computing Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","author":"blond\u00e9","year":"2021","journal-title":"ArXiv"},{"key":"ref33","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"ArXiv"},{"key":"ref32","article-title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","author":"nachum","year":"2019","journal-title":"Optimization Foundations for Reinforcement Learning Workshop at NeurIPS 2019"},{"key":"ref31","article-title":"Reinforcement Learning with Deep Energy-Based Policies","author":"haarnoja","year":"2017","journal-title":"ArXiv"},{"key":"ref30","article-title":"Off-Policy Adversarial Inverse Reinforcement Learning","author":"arnob","year":"2020","journal-title":"ArXiv"},{"key":"ref37","article-title":"Robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","author":"zhu","year":"2020","journal-title":"ArXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref35","article-title":"Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning","author":"ota","year":"2020","journal-title":"International Conference on Intelligent Robots and System"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340915"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref11","article-title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","author":"kostrikov","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3005126"},{"key":"ref13","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref14","article-title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","author":"blond\u00e9","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref15","article-title":"Sample Efficient Imitation Learning for Continuous Control","author":"sasaki","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref16","article-title":"Imitation Learning via Off-Policy Distribution Matching","author":"kostrikov","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref17","first-page":"12402","article-title":"Off-Policy Imitation Learning from Observations","volume":"33","author":"zhu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"1259","article-title":"A Divergence Minimization Perspective on Imitation Learning Methods","author":"ghasemipour","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref19","author":"nachum","year":"2016","journal-title":"Improving Policy Gradient by Exploring Under-appreciated Rewards"},{"key":"ref4","article-title":"End to End Learning for Self-Driving Cars","author":"bojarski","year":"2016","journal-title":"ArXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE50665.2020.9291841"},{"key":"ref6","article-title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","author":"fu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref5","article-title":"Generative Adversarial Imitation Learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"7194","article-title":"Multi-Agent Adversarial Inverse Reinforcement Learning","author":"yu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref7","article-title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","volume":"32","author":"yu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Cooperative Inverse Reinforcement Learning","volume":"29","author":"hadfield-menell","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Algorithms for Inverse Reinforcement Learning","author":"ng","year":"2000","journal-title":"17th International Conference on Machine Learning"},{"key":"ref1","article-title":"Concrete Problems in AI Safety","author":"amodei","year":"2016","journal-title":"ArXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref22","article-title":"Generative Adversarial Nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"6","article-title":"Maximum Entropy Inverse Reinforcement Learning","author":"ziebart","year":"0","journal-title":"Proceedings of the 23rd National Conference on Artificial Intelligence"},{"key":"ref24","article-title":"F-IRL: Inverse Reinforcement Learning via State Marginal Matching","author":"ni","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref23","first-page":"49","article-title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","author":"finn","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48"},{"key":"ref26","article-title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","author":"sun","year":"2021","journal-title":"ArXiv"},{"key":"ref25","article-title":"DualDICE: Efficient Estimation of Off-Policy Stationary Distribution Corrections","author":"nachum","year":"2019","journal-title":"ICML 2019 Workshop RL4RealLife"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811660.pdf?arnumber=9811660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:06:39Z","timestamp":1667516799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811660","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}