IDEAS home Printed from https://ideas.repec.org/a/plo/pcbi00/1006827.html
   My bibliography  Save this article

Optimizing the depth and the direction of prospective planning using information values

Author

Listed:
  • Can Eren Sezener
  • Amir Dezfouli
  • Mehdi Keramati

Abstract

Evaluating the future consequences of actions is achievable by simulating a mental search tree into the future. Expanding deep trees, however, is computationally taxing. Therefore, machines and humans use a plan-until-habit scheme that simulates the environment up to a limited depth and then exploits habitual values as proxies for consequences that may arise in the future. Two outstanding questions in this scheme are “in which directions the search tree should be expanded?”, and “when should the expansion stop?”. Here we propose a principled solution to these questions based on a speed/accuracy tradeoff: deeper expansion in the appropriate directions leads to more accurate planning, but at the cost of slower decision-making. Our simulation results show how this algorithm expands the search tree effectively and efficiently in a grid-world environment. We further show that our algorithm can explain several behavioral patterns in animals and humans, namely the effect of time-pressure on the depth of planning, the effect of reward magnitudes on the direction of planning, and the gradual shift from goal-directed to habitual behavior over the course of training. The algorithm also provides several predictions testable in animal/human experiments.Author summary: When faced with several choices in complex environments like chess, thinking about all the potential consequences of each choice, infinitely deep into the future, is simply impossible due to time and cognitive limitations. An outstanding question is what is the best direction and depth of thinking about the future? Here we propose a mathematical algorithm that computes, along the course of planning, the benefit of thinking another step in a given direction into the future, and compares that with the cost of thinking in order to compute the net benefit. We show that this algorithm is consistent with several behavioral patterns observed in humans and animals, suggesting that they, too, make efficient use of their time and cognitive resources when deciding how deep to think.

Suggested Citation

  • Can Eren Sezener & Amir Dezfouli & Mehdi Keramati, 2019. "Optimizing the depth and the direction of prospective planning using information values," PLOS Computational Biology, Public Library of Science, vol. 15(3), pages 1-21, March.
  • Handle: RePEc:plo:pcbi00:1006827
    DOI: 10.1371/journal.pcbi.1006827
    as

    Download full text from publisher

    File URL: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006827
    Download Restriction: no

    File URL: https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006827&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pcbi.1006827?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. Julie J Lee & Mehdi Keramati, 2017. "Flexibility to contingency changes distinguishes habitual and goal-directed strategies in humans," PLOS Computational Biology, Public Library of Science, vol. 13(9), pages 1-15, September.
    2. David Silver & Aja Huang & Chris J. Maddison & Arthur Guez & Laurent Sifre & George van den Driessche & Julian Schrittwieser & Ioannis Antonoglou & Veda Panneershelvam & Marc Lanctot & Sander Dieleman, 2016. "Mastering the game of Go with deep neural networks and tree search," Nature, Nature, vol. 529(7587), pages 484-489, January.
    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. Xiaoyue Li & John M. Mulvey, 2023. "Optimal Portfolio Execution in a Regime-switching Market with Non-linear Impact Costs: Combining Dynamic Program and Neural Network," Papers 2306.08809, arXiv.org.
    2. Nathan Companez & Aldeida Aleti, 2016. "Can Monte-Carlo Tree Search learn to sacrifice?," Journal of Heuristics, Springer, vol. 22(6), pages 783-813, December.
    3. Zhewei Zhang & Youngjin Yoo & Kalle Lyytinen & Aron Lindberg, 2021. "The Unknowability of Autonomous Tools and the Liminal Experience of Their Use," Information Systems Research, INFORMS, vol. 32(4), pages 1192-1213, December.
    4. Yuhong Wang & Lei Chen & Hong Zhou & Xu Zhou & Zongsheng Zheng & Qi Zeng & Li Jiang & Liang Lu, 2021. "Flexible Transmission Network Expansion Planning Based on DQN Algorithm," Energies, MDPI, vol. 14(7), pages 1-21, April.
    5. Gokhale, Gargya & Claessens, Bert & Develder, Chris, 2022. "Physics informed neural networks for control oriented thermal modeling of buildings," Applied Energy, Elsevier, vol. 314(C).
    6. Li Xia, 2020. "Risk‐Sensitive Markov Decision Processes with Combined Metrics of Mean and Variance," Production and Operations Management, Production and Operations Management Society, vol. 29(12), pages 2808-2827, December.
    7. Neha Soni & Enakshi Khular Sharma & Narotam Singh & Amita Kapoor, 2019. "Impact of Artificial Intelligence on Businesses: from Research, Innovation, Market Deployment to Future Shifts in Business Models," Papers 1905.02092, arXiv.org.
    8. Yin, Linfei & He, Xiaoyu, 2023. "Artificial emotional deep Q learning for real-time smart voltage control of cyber-physical social power systems," Energy, Elsevier, vol. 273(C).
    9. Taejong Joo & Hyunyoung Jun & Dongmin Shin, 2022. "Task Allocation in Human–Machine Manufacturing Systems Using Deep Reinforcement Learning," Sustainability, MDPI, vol. 14(4), pages 1-18, February.
    10. Burka, Dávid & Puppe, Clemens & Szepesváry, László & Tasnádi, Attila, 2022. "Voting: A machine learning approach," European Journal of Operational Research, Elsevier, vol. 299(3), pages 1003-1017.
    11. Oleh Lukianykhin & Tetiana Bogodorova, 2021. "Voltage Control-Based Ancillary Service Using Deep Reinforcement Learning," Energies, MDPI, vol. 14(8), pages 1-22, April.
    12. De Bruyn, Arnaud & Viswanathan, Vijay & Beh, Yean Shan & Brock, Jürgen Kai-Uwe & von Wangenheim, Florian, 2020. "Artificial Intelligence and Marketing: Pitfalls and Opportunities," Journal of Interactive Marketing, Elsevier, vol. 51(C), pages 91-105.
    13. Zhimian Chen & Yizeng Wang & Hao Hu & Zhipeng Zhang & Chengwei Zhang & Shukun Zhou, 2024. "Investigating Autonomous Vehicle Driving Strategies in Highway Ramp Merging Zones," Mathematics, MDPI, vol. 12(23), pages 1-22, December.
    14. Keerthana Sivamayil & Elakkiya Rajasekar & Belqasem Aljafari & Srete Nikolovski & Subramaniyaswamy Vairavasundaram & Indragandhi Vairavasundaram, 2023. "A Systematic Study on Reinforcement Learning Based Applications," Energies, MDPI, vol. 16(3), pages 1-23, February.
    15. Chen, Jiaxin & Shu, Hong & Tang, Xiaolin & Liu, Teng & Wang, Weida, 2022. "Deep reinforcement learning-based multi-objective control of hybrid power system combined with road recognition under time-varying environment," Energy, Elsevier, vol. 239(PC).
    16. Amirhosein Mosavi & Yaser Faghan & Pedram Ghamisi & Puhong Duan & Sina Faizollahzadeh Ardabili & Ely Salwana & Shahab S. Band, 2020. "Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics," Mathematics, MDPI, vol. 8(10), pages 1-42, September.
    17. Zhang, Yihao & Chai, Zhaojie & Lykotrafitis, George, 2021. "Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 571(C).
    18. Haoran Wang & Xun Yu Zhou, 2020. "Continuous‐time mean–variance portfolio selection: A reinforcement learning framework," Mathematical Finance, Wiley Blackwell, vol. 30(4), pages 1273-1308, October.
    19. Keller, Alexander & Dahm, Ken, 2019. "Integral equations and machine learning," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 161(C), pages 2-12.
    20. Zhang, Yiwen & Lin, Rui & Mei, Zhen & Lyu, Minghao & Jiang, Huaiguang & Xue, Ying & Zhang, Jun & Gao, David Wenzhong, 2024. "Interior-point policy optimization based multi-agent deep reinforcement learning method for secure home energy management under various uncertainties," Applied Energy, Elsevier, vol. 376(PA).

    More about this item

    Statistics

    Access and download statistics

    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:plo:pcbi00:1006827. 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: ploscompbiol (email available below). General contact details of provider: https://journals.plos.org/ploscompbiol/ .

    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.