{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:18:02Z","timestamp":1792790282046,"version":"4.5.0"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1109\/tpami.2022.3215769","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:45:08Z","timestamp":1667511908000},"page":"1-15","source":"Crossref","is-referenced-by-count":3,"title":["Continuous-Time Fitted Value Iteration for Robust Policies"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9019-6769","authenticated-orcid":false,"given":"Michael","family":"Lutter","sequence":"first","affiliation":[{"name":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Belousov","sequence":"additional","affiliation":[{"name":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shie","family":"Mannor","sequence":"additional","affiliation":[{"name":"The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion-Israel Institute of Technology and a Distinguished Scientist at NVIDIA, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[{"name":"Allen School of Computer Science & Engineering, University of Washington and Senior Director of Robotics Research at NVIDIA, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0482-4296","authenticated-orcid":false,"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Toronto, Member of the Vector Institute and Senior Scientist at NVIDIA, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-8091","authenticated-orcid":false,"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g0s"},{"key":"ref2","volume-title":"Foundations of Mathematical Economics","author":"Carter","year":"2001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511806827"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7331044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899249"},{"key":"ref11","first-page":"640","article-title":"HJB optimal feedback control with deep differential value functions and action constraints","volume-title":"Proc. Conf. Robot Learn.","author":"Lutter"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.848292"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"key":"ref14","first-page":"739","article-title":"Hamilton-Jacobi-Bellman equations for Q-learning in continuous time","author":"Kim","year":"2020","journal-title":"Proc. Learn. Dyn. Control"},{"key":"ref15","article-title":"Hamilton-Jacobi deep Q-Learning for deterministic continuous-time systems with lipschitz continuous controls","author":"Kim","year":"2020"},{"key":"ref16","first-page":"7224","article-title":"Value iteration in continuous actions, states and time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lutter"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.694659"},{"key":"ref19","volume-title":"Optimal Control Theory: An Introduction","author":"Kirk","year":"1970"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0176"},{"key":"ref22","volume-title":"Differential Games: A Mathematical Theory with Applications to Warfare and Pursuit, Control and Optimization","author":"Isaacs","year":"1999"},{"key":"ref23","article-title":"Robust deep reinforcement learning against adversarial perturbations on observations","author":"Zhang","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref28","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989190"},{"key":"ref30","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tessler"},{"key":"ref31","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"Pattanaik","year":"2017"},{"key":"ref32","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"Gleave","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5268-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74358-3_9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2000.879537"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511976476"},{"key":"ref38","volume-title":"Controlled Markov Processes and Viscosity Solutions","author":"Fleming","year":"2006"},{"key":"ref39","first-page":"369","article-title":"Generalization in reinforcement learning: Safely approximating the value function","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Boyan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref42","first-page":"59","article-title":"Finite-time bounds for fitted value iteration","volume":"22","author":"Munos","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992697"},{"issue":"18","key":"ref46","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160611"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref51","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref52","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref53","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018"},{"key":"ref54","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buckman"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref56","article-title":"Rl unplugged: Benchmarks for offline reinforcement learning","author":"Gulcehre","year":"2020"},{"key":"ref57","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","volume-title":"Proc. Conf. Robot Learn.","author":"Muratore"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref59","first-page":"7224","article-title":"Value iteration in continuous actions, states and time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lutter"},{"key":"ref60","volume-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref61","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref62","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berkenkamp"},{"key":"ref63","article-title":"The lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems","author":"Richards","year":"2018"},{"key":"ref64","first-page":"11128","article-title":"Learning stable deep dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolter"},{"key":"ref65","first-page":"3245","article-title":"Neural lyapunov control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chang"},{"key":"ref66","article-title":"Conservative safety critics for exploration","author":"Bharadhwaj","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref67","article-title":"Quanser courseware and resources","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref69","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref70","article-title":"Making deep q-learning methods robust to time discretization","author":"Tallec","year":"2019"},{"key":"ref71","article-title":"Deep lagrangian networks: Using physics as model prior for deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lutter"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968268"},{"key":"ref73","first-page":"15379","article-title":"Hamiltonian neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Greydanus"},{"key":"ref74","article-title":"Symplectic ode-net: Learning hamiltonian dynamics with control","author":"Zhong","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"ref76","article-title":"Model-based path integral stochastic control: A Bayesian nonparametric approach","author":"Pan","year":"2014"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2544787"},{"key":"ref78","article-title":"Learning deep stochastic optimal control policies using forward-backward SDEs","volume-title":"Proc. Robot.: Sci. Syst.","author":"Pereira"},{"key":"ref79","article-title":"Safe optimal control using stochastic barrier functions and deep forward-backward sdes","author":"Pereira","year":"2020"},{"key":"ref80","first-page":"325","article-title":"Optimal reinforcement learning for gaussian systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hennig"},{"key":"ref81","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(01)00152-9"},{"key":"ref83","article-title":"Risk-sensitive and robust decision-making: A CVaR optimization approach","author":"Chow","year":"2015"},{"key":"ref84","article-title":"Scaling up robust MDPs by reinforcement learning","author":"Tamar","year":"2013"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_34"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.077"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.029"},{"key":"ref91","article-title":"Simurlacra - a framework for reinforcement learning from randomized simulations","author":"Muratore","year":"2020"},{"key":"ref92","article-title":"MushroomRL: Simplifying reinforcement learning research","author":"D\u2019Eramo","year":"2020"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref94","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09925102.pdf?arnumber=9925102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:35:57Z","timestamp":1705962957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9925102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3215769","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":[[2022]]}}}