Home > Research > Researchers > Professor David Leslie > Publications

Professor David Leslie

Professor

  1. Journal article
  2. Published

    Learning in unknown reward games: application to sensor networks

    Chapman, A. C., Leslie, D. S., Rogers, A. & Jennings, N. R., 1/06/2014, In: The Computer Journal. 57, 6, p. 875-892 18 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  3. Published

    Context-dependent decision-making: a simple Bayesian model

    Lloyd, K. & Leslie, D. S., 20/02/2013, In: Interface. 10, 82, p. 1-13 13 p., 20130069.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  4. Published

    Convergent learning algorithms for unknown reward games

    Chapman, A. C., Leslie, D. S., Rogers, A. & Jennings, N. R., 1/01/2013, In: SIAM Journal on Control and Optimization. 51, 4, p. 3154-3180 27 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  5. Published

    Respondent driven sampling and community structure in a population of injecting drug users, Bristol, UK

    Mills, H. L., Colijn, C., Vickerman, P., Leslie, D. S., Hope, V. & Hickman, M., 1/12/2012, In: Drug and Alcohol Dependence. 126, 3, p. 324-332 8 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  6. Published

    Optimistic Bayesian sampling in contextual-bandit problems

    May, B. C., Korda, N., Lee, A. & Leslie, D. S., 06/2012, In: Journal of Machine Learning Research. 13, p. 2069-2106 37 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  7. Published

    Asynchronous stochastic approximation with differential inclusions

    Perkins, S. & Leslie, D. S., 2012, In: Stochastic Systems. 2, p. 409-446 37 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  8. Published

    Information theory and observational limitations in decision making

    Wolpert, D. & Leslie, D. S., 2012, In: BE Journal of Theoretical Economics. 12, 1

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  9. Unpublished

    Adaptive forgetting factor fictitious play

    Smyrnakis, M. & S. Leslie, D., 11/12/2011, (Unpublished) In: arxiv.org.

    Research output: Contribution to Journal/MagazineJournal article

  10. Published

    A unifying framework for iterative approximate best-response algorithms for distributed constraint optimization problems

    Chapman, A. C., Rogers, A., Jennings, N. R. & Leslie, D. S., 1/12/2011, In: Knowledge Engineering Review. 26, 04, p. 411-444 34 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  11. Published

    Dynamic opponent modelling in fictitious play

    Smyrnakis, M. & Leslie, D. S., 1/11/2010, In: The Computer Journal. 53, 9, p. 1344-1359 15 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  12. Published

    Posterior weighted reinforcement learning with state uncertainty

    Larsen, T., Leslie, D. S., Collins, E. J. & Bogacz, R., 1/05/2010, In: Neural Computation. 22, 5, p. 1149-1179 30 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  13. Published

    Nonparametric estimation of the distribution function in contingent valuation models

    Leslie, D. S., Kohn, R. & Fiebig, D. G., 1/09/2009, In: Bayesian Analysis. 4, 3, p. 573-598 15 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  14. Published

    Generalised linear mixed model analysis via sequential Monte Carlo sampling

    Fan, Y., Leslie, D. S. & Wand, M. P., 1/01/2008, In: Electronic Journal of Statistics. 2, p. 916-938 22 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  15. Published

    On similarities between inference in game theory and machine learning

    Rezek, I., Leslie, D. S., Reece, S., Roberts, S. J., Rogers, A., Dash, R. K. & Jennings, N. R., 2008, In: Journal of Artificial Intelligence Research. 33, p. 259-283 24 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  16. Published

    A general approach to heteroscedastic linear regression

    Leslie, D. S., Kohn, R. & Nott, D. J., 25/05/2007, In: Statistics and Computing. 17, 2, p. 131-146 15 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  17. Published

    Generalised weakened fictitious play

    Leslie, D. S. & Collins, E. J., 1/08/2006, In: Games and Economic Behavior. 56, 2, p. 285-298 13 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  18. Published

    Individual Q-learning in normal form games

    Leslie, D. S. & Collins, E. J., 1/01/2005, In: SIAM Journal on Control and Optimization. 44, 2, p. 495-514 20 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  19. Published

    Convergent multiple-timescales reinforcement learning algorithms in normal form games

    Leslie, D. S., 2003, In: Annals of Applied Probability. 13, 4, p. 1231-1251 21 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

  20. Comment/debate
  21. Published

    Discussion on the paper by Handcock, Raftery and Tantrum

    Leslie, D. S., 1/03/2007, In: Journal of the Royal Statistical Society: Series A Statistics in Society. 170, 2, p. 328-329 2 p.

    Research output: Contribution to Journal/MagazineComment/debatepeer-review

  22. Working paper
  23. Published

    Population-level reinforcement learning resulting in smooth best response dynamics

    Leslie, D. S. & Collins, E. J., 2002, p. 1-13, 14 p.

    Research output: Working paper

  24. Preprint
  25. Published
  26. Published

    Gaussian Processes on Hypergraphs

    Pinder, T., Turnbull, K., Nemeth, C. & Leslie, D., 3/06/2021.

    Research output: Working paperPreprint

Previous 1 2 3 Next

Back to top