IDEAS home Printed from https://ideas.repec.org/a/inm/ormoor/v42y2017i3p762-782.html
   My bibliography  Save this article

Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization

Author

Listed:
  • Zheng Wen

    (Adobe Research, San Jose, California 95110)

  • Benjamin Van Roy

    (Stanford University, Stanford, California 94305)

Abstract

We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation ( OCP ), an algorithm designed to synthesize efficient exploration and value function generalization. We establish that when the true value function lies within a given hypothesis class, OCP selects optimal actions over all but at most D episodes, where D is the eluder dimension of the given hypothesis class. We establish further efficiency and asymptotic performance guarantees that apply even if the true value function does not lie in the given hypothesis class, for the special case where the hypothesis class is the span of prespecified indicator functions over disjoint sets. We also discuss the computational complexity of OCP and present computational results involving two illustrative examples.

Suggested Citation

  • Zheng Wen & Benjamin Van Roy, 2017. "Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization," Mathematics of Operations Research, INFORMS, vol. 42(3), pages 762-782, August.
    • Handle: RePEc:inm:ormoor:v:42:y:2017:i:3:p:762-782
    DOI: 10.1287/moor.2016.0826
    as

    Download full text from publisher

    File URL: https://doi.org/10.1287/moor.2016.0826
    Download Restriction: no
    File URL: https://libkey.io/10.1287/moor.2016.0826?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Benjamin Van Roy, 2006. "Performance Loss Bounds for Approximate Value Iteration with State Aggregation," Mathematics of Operations Research, INFORMS, vol. 31(2), pages 234-244, May.
    2. Daniel Russo & Benjamin Van Roy, 2014. "Learning to Optimize via Posterior Sampling," Mathematics of Operations Research, INFORMS, vol. 39(4), pages 1221-1243, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. David Simchi-Levi & Rui Sun & Huanan Zhang, 2022. "Online Learning and Optimization for Revenue Management Problems with Add-on Discounts," Management Science, INFORMS, vol. 68(10), pages 7402-7421, October.
    2. Hamsa Bastani & David Simchi-Levi & Ruihao Zhu, 2022. "Meta Dynamic Pricing: Transfer Learning Across Experiments," Management Science, INFORMS, vol. 68(3), pages 1865-1881, March.
    3. Zhengyuan Zhou & Susan Athey & Stefan Wager, 2023. "Offline Multi-Action Policy Learning: Generalization and Optimization," Operations Research, INFORMS, vol. 71(1), pages 148-183, January.
    4. Rong Jin & David Simchi-Levi & Li Wang & Xinshang Wang & Sen Yang, 2021. "Shrinking the Upper Confidence Bound: A Dynamic Product Selection Problem for Urban Warehouses," Management Science, INFORMS, vol. 67(8), pages 4756-4771, August.
    5. Xiangyu Gao & Stefanus Jasin & Sajjad Najafi & Huanan Zhang, 2022. "Joint Learning and Optimization for Multi-Product Pricing (and Ranking) Under a General Cascade Click Model," Management Science, INFORMS, vol. 68(10), pages 7362-7382, October.
    6. Chevalier, Philippe & Lamas, Alejandro & Lu, Liang & Mlinar, Tanja, 2015. "Revenue management for operations with urgent orders," European Journal of Operational Research, Elsevier, vol. 240(2), pages 476-487.
    7. Mengying Zhu & Xiaolin Zheng & Yan Wang & Yuyuan Li & Qianqiao Liang, 2019. "Adaptive Portfolio by Solving Multi-armed Bandit via Thompson Sampling," Papers 1911.05309, arXiv.org, revised Nov 2019.
    8. T. Law & J. Shawe-Taylor, 2017. "Practical Bayesian support vector regression for financial time series prediction and market condition change detection," Quantitative Finance, Taylor & Francis Journals, vol. 17(9), pages 1403-1416, September.
    9. Rodriguez, Sergio & Ludkovski, Michael, 2020. "Probabilistic bisection with spatial metamodels," European Journal of Operational Research, Elsevier, vol. 286(2), pages 588-603.
    10. Maria Dimakopoulou & Zhimei Ren & Zhengyuan Zhou, 2021. "Online Multi-Armed Bandits with Adaptive Inference," Papers 2102.13202, arXiv.org, revised Jun 2021.
    11. Anand Kalvit & Aleksandrs Slivkins & Yonatan Gur, 2024. "Incentivized Exploration via Filtered Posterior Sampling," Papers 2402.13338, arXiv.org.
    12. Jia Hao & Mengying Zhou & Guoxin Wang & Liangyue Jia & Yan Yan, 2020. "Design optimization by integrating limited simulation data and shape engineering knowledge with Bayesian optimization (BO-DK4DO)," Journal of Intelligent Manufacturing, Springer, vol. 31(8), pages 2049-2067, December.
    13. Ilya O. Ryzhov & Martijn R. K. Mes & Warren B. Powell & Gerald van den Berg, 2019. "Bayesian Exploration for Approximate Dynamic Programming," Operations Research, INFORMS, vol. 67(1), pages 198-214, January.
    14. Ruohan Zhan & Zhimei Ren & Susan Athey & Zhengyuan Zhou, 2021. "Policy Learning with Adaptively Collected Data," Papers 2105.02344, arXiv.org, revised Nov 2022.
    15. Ilya O. Ryzhov, 2016. "On the Convergence Rates of Expected Improvement Methods," Operations Research, INFORMS, vol. 64(6), pages 1515-1528, December.
    16. Dimitris Bertsimas & Velibor V. Mišić, 2016. "Decomposable Markov Decision Processes: A Fluid Optimization Approach," Operations Research, INFORMS, vol. 64(6), pages 1537-1555, December.
    17. Nicolás Aramayo & Mario Schiappacasse & Marcel Goic, 2023. "A Multiarmed Bandit Approach for House Ads Recommendations," Marketing Science, INFORMS, vol. 42(2), pages 271-292, March.
    18. Guy Aridor & Yishay Mansour & Aleksandrs Slivkins & Zhiwei Steven Wu, 2020. "Competing Bandits: The Perils of Exploration Under Competition," Papers 2007.10144, arXiv.org, revised Dec 2022.
    19. Po-Yi Liu & Chi-Hua Wang & Henghsiu Tsai, 2022. "Non-Stationary Dynamic Pricing Via Actor-Critic Information-Directed Pricing," Papers 2208.09372, arXiv.org, revised Sep 2022.
    20. Sareh Nabi & Houssam Nassif & Joseph Hong & Hamed Mamani & Guido Imbens, 2022. "Bayesian Meta-Prior Learning Using Empirical Bayes," Management Science, INFORMS, vol. 68(3), pages 1737-1755, March.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:inm:ormoor:v:42:y:2017:i:3:p:762-782. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Chris Asher (email available below). General contact details of provider: https://edirc.repec.org/data/inforea.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.