04584nam 2200649Ii 45000010011000000030004000110050017000150060024000320070015000560080041000710200030001120200025001420240028001670400030001950500025002250820015002501000041002652450108003062640056004143000026004703360021004963370026005173380032005434900091005755040057006665050023007235050194007465050255009405050142011955050140013375050070014775060065015475100019016125100023016315100011016545100011016655100024016765100039017005100031017395100019017705100026017895201411018155240191032265300029034175380036034465380047034825880050035296500028035796500022036076550022036297000024036517000026036757100032037017760034037338300092037678560075038592600000023NOW20210219190106.0m eo d cr cn |||m|||a190401s2020 mau ob 000 0 eng d a9781680837537qelectronic z9781680837520qprint7 a10.1561/26000000232doi aCaBNVSLcCaBNVSLdCaBNVSL 4aQ325.6 $b.J53 2020eb04a006.312231 aJiang, Z.-P.q(Zhong-Ping),eauthor.10aLearning-based control :ba tutorial and some recent results /cZhong-Ping Jiang, Tao Bian, Weinan Gao. 1a[Hanover, Massachusetts] :bNow Publishers,c2020. a1 PDF (pages 176-284) atext2rdacontent aelectronic2isbdmedia aonline resource2rdacarrier1 aFoundations and trends in systems and control,x2325-6826 ;vVol. 8: No. 3, pp 176-284 aIncludes bibliographical references (pages 264-284).0 a1. Introduction --8 a2. Learning-based control of continuous-time dynamical systems. 2.1. Uncertain linear time-invariant systems ; 2.2. Uncertain linear stochastic systems ; 2.3. Uncertain nonlinear systems --8 a3. Learning-based control of large-scale interconnected systems. 3.1. Input-to-state stability and small-gain techniques ; 3.2. Robust optimal control for large-scale systems ; 3.3. Decentralized learning-based controllers for large-scale systems -- 8 a4. Learning-based output regulation. 4.1. Uncertain linear systems ; 4.2. Nonlinear strict-feedback systems ; 4.3. Multi-agent systems --8 a5. Applications. 5.1. Model-free optimal biological motor control ; 5.2. Learning-based control of connected and autonomous vehicles --8 a6. Perspective and future work -- Acknowledgements -- References. aRestricted to subscribers or individual document purchasers.0 aGoogle Scholar0 aGoogle Book Search0 aINSPEC0 aScopus0 aACM Computing Guide0 aDBLP Computer Science Bibliography0 aZentralblatt MATH Database0 aAMS MathSciNet0 aACM Computing Reviews3 aThis monograph presents a new framework for learning-based control synthesis of continuous-time dynamical systems with unknown dynamics. The new design paradigm proposed here is fundamentally different from traditional control theory. In the classical paradigm, controllers are often designed for a given class of dynamical control systems; it is a model-based design. Under the learning-based control framework, controllers are learned online from real-time input-output data collected along the trajectories of the control system in question. An entanglement of techniques from reinforcement learning and model-based control theory is advocated to find a sequence of suboptimal controllers that converge to the optimal solution as learning steps increase. On the one hand, this learning-based design approach attempts to overcome the well-known "curse of dimensionality" and the "curse of modeling" associated with Bellman's Dynamic Programming. On the other hand, rigorous stability and robustness analysis can be derived for the closed-loop system with real-time learning-based controllers. The effectiveness of the proposed learning-based control framework is demonstrated via its applications to theoretical optimal control problems tied to various important classes of continuous-time dynamical systems and practical problems arising from biological motor control, connected and autonomous vehicles. aZhong-Ping Jiang, Tao Bian and Weinan Gao (2020), "Learning-Based Control: A Tutorial and Some Recent Results", Foundations and Trends in Systems and Control: Vol. 8: No. 3, pp 176-284. aAlso available in print. aMode of access: World Wide Web. aSystem requirements: Adobe Acrobat reader. aTitle from PDF (viewed on February 16, 2021). 0aReinforcement learning. 0aMachine learning. 0aElectronic books.1 aBian, Tao,eauthor.1 aGao, Weinan,eauthor.2 aNow Publishers,epublisher.08iPrint version:z9781680837520 0aFoundations and trends in systems and control ;vVol. 8: No. 3, pp 176-284.x2325-6826 483Abstract with links to full textuhttp://dx.doi.org/10.1561/2600000023