On Learning the Optimal Waiting Time

  • Tor Lattimore
  • András György
  • Csaba Szepesvári
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8776)


Consider the problem of learning how long to wait for a bus before walking, experimenting each day and assuming that the bus arrival times are independent and identically distributed random variables with an unknown distribution. Similar uncertain optimal stopping problems arise when devising power-saving strategies, e.g., learning the optimal disk spin-down time for mobile computers, or speeding up certain types of satisficing search procedures by switching from a potentially fast search method that is unreliable, to one that is reliable, but slower. Formally, the problem can be described as a repeated game. In each round of the game an agent is waiting for an event to occur. If the event occurs while the agent is waiting, the agent suffers a loss that is the sum of the event’s “arrival time” and some fixed loss. If the agents decides to give up waiting before the event occurs, he suffers a loss that is the sum of the waiting time and some other fixed loss. It is assumed that the arrival times are independent random quantities with the same distribution, which is unknown, while the agent knows the loss associated with each outcome. Two versions of the game are considered. In the full information case the agent observes the arrival times regardless of its actions, while in the partial information case the arrival time is observed only if it does not exceed the waiting time. After some general structural observations about the problem, we present a number of algorithms for both cases that learn the optimal weighting time with nearly matching minimax upper and lower bounds on their regret.


Arrival Time Partial Information Information Setting Stochastic Local Search Minimax Regret 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agrawal, R., Teneketzis, D., Anantharam, V.: Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: Finite parameter space. IEEE Transaction on Automatic Control 34, 258–267 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Alon, N., Cesa-Bianchi, N., Gentile, C., Mansour, Y.: From bandits to experts: A tale of domination and independence. In: Advances in Neural Information Processing Systems, pp. 1610–1618 (2013)Google Scholar
  3. 3.
    Bartók, G.: A near-optimal algorithm for finite partial-monitoring games against adversarial opponents. In: COLT, pp. 696–710 (2013)Google Scholar
  4. 4.
    Bartók, G., Pál, D., Szepesvári, C.: Minimax regret of finite partial-monitoring games in stochastic environments. In: COLT 2011, pp. 133–154 (2011)Google Scholar
  5. 5.
    Cesa-Bianchi, N.: Prediction, learning, and games. Cambridge University Press (2006)Google Scholar
  6. 6.
    Cohen, A.C.: Truncated and censored samples: theory and applications. CRC Press (1991)Google Scholar
  7. 7.
    Devroye, L., Lugosi, G.: Combinatorial methods in density estimation. Springer (2001)Google Scholar
  8. 8.
    Dvoretzky, A., Kiefer, J., Wolfowitz, J.: Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator. The Annals of Mathematical Statistics 27, 642–669 (1956)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Foster, D.P., Rakhlin, A.: No internal regret via neighborhood watch. Journal of Machine Learning Research - Proceedings Track (AISTATS) 22, 382–390 (2012)Google Scholar
  10. 10.
    Ganchev, K., Nevmyvaka, Y., Kearns, M., Vaughan, J.W.: Censored exploration and the dark pool problem. Communications of the ACM 53(5), 99–107 (2010)CrossRefGoogle Scholar
  11. 11.
    Kleinberg, R., Leighton, T.: The value of knowing a demand curve: Bounds on regret for online posted-price auctions. In: Proceedings of the 44th Annual IEEE Symposium on Foundations of Computer Science, pp. 594–605. IEEE (2003)Google Scholar
  12. 12.
    Krishnan, P., Long, P.M., Vitter, J.S.: Adaptive disk spindown via optimal rent-to-buy in probabilistic environments. Algorithmica 23(1), 31–56 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Lattimore, T., György, A., Szepesvári, C.: On learning the optimal waiting time (2014),
  14. 14.
    Mannor, S., Shamir, O.: From bandits to experts: On the value of side-observations. In: NIPS, pp. 684–692 (2011)Google Scholar
  15. 15.
    Massart, P.: The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. The Annals of Probability 18, 1269–1283 (1990)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Ribeiro, C.C., Rosseti, I., Vallejos, R.: Exploiting run time distributions to compare sequential and parallel stochastic local search algorithms. Journal of Global Optimization 54(2), 405–429 (2012)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Tor Lattimore
    • 1
  • András György
    • 1
  • Csaba Szepesvári
    • 1
    • 2
  1. 1.Department of Computing ScienceUniversity of AlbertaCanada
  2. 2.Microsoft ResearchRedmondUSA

Personalised recommendations