Peter Auer, Nicol{\`{o}} Cesa-Bianchi, , and Claudio Gentile.
  Adaptive and self-confident on-line learning algorithms.
  \emph{JCSS}, 64\penalty0 (1):\penalty0 48--75, 2002{\natexlab{a}}.
  (A preliminary version has appeared in Proc. 13th Ann. Conf.
  Computational Learning Theory.).

Peter Auer, Nicol\`o Cesa-Bianchi, Yoav Freund, and Robert  E. Schapire.
  The nonstochastic multiarmed bandit problem.
  \emph{SIAM Journal on Computing}, 32\penalty0 (1):\penalty0 48--77,
  2002{\natexlab{b}}.

Nicol\`o Cesa-Bianchi, Yoav Freund, David  P. Helmbold, David Haussler,
  Robert  E. Schapire, and Manfred  K. Warmuth.
  How to use expert advice.
  In \emph{STOC}, pages 382--391, 1993.
  Also, {\it Journal of the Association for Computing Machinery},
  44(3): 427-485 (1997).

Nicol{\`{o}} Cesa-Bianchi and G\'{a}bor Lugosi.
  Potential-based algorithms in on-line prediction and game theory.
  \emph{Machine Learning}, 51\penalty0 (3):\penalty0 239--261, 2003.

Nicol\`o Cesa-Bianchi, G\'{a}bor Lugosi, and Gilles Stoltz.
  Regret minimization under partial monitoring.
  unpublished manuscript, 2004.

Nicol\`o Cesa-Bianchi, Yishay Mansour, and Gilles Stoltz.
  Improved second-order bounds for prediction with expert advice.
  In \emph{COLT}, 2005.

D.  Foster and R.  Vohra.
  Calibrated learning and correlated equilibrium.
  \emph{Games and Economic Behavior}, 21:\penalty0 40--55, 1997.

D.  Foster and R.  Vohra.
  Asymptotic calibration.
  \emph{Biometrika}, 85:\penalty0 379--390, 1998.

D.  Foster and R.  Vohra.
  Regret in the on-line decision problem.
  \emph{Games and Economic Behavior}, 29:\penalty0 7--36, 1999.

Dean  P. Foster and Rakesh  V. Vohra.
  A randomization rule for selecting forecasts.
  \emph{Operations Research}, 41\penalty0 (4):\penalty0 704--709,
  July--August 1993.

Y.  Freund, R.  Schapire, Y.  Singer, and M.  Warmuth.
  Using and combining predictors that specialize.
  In \emph{Proceedings of the 29th Annual Symposium on Theory of
  Computing}, pages 334--343, 1997.

Yoav Freund and Robert  E. Schapire.
  A decision-theoretic generalization of on-line learning and an
  application to boosting.
  In \emph{Euro-COLT}, pages 23--37. Springer-Verlag, 1995.
  Also, JCSS 55(1): 119-139 (1997).

Yoav Freund and Robert  E. Schapire.
  Adaptive game playing using multiplicative weights.
  \emph{Games and Economic Behavior}, 29:\penalty0 79--103, 1999.
  (A preliminary version appeared in the Proceedings of the Ninth
  Annual Conference on Computational Learning Theory, pages 325--332, 1996.).

\bibitem[Hart and Mas-Colell(2000)]{HM}
S.  Hart and A.  Mas-Colell.
  A simple adaptive procedure leading to correlated equilibrium.
  \emph{Econometrica}, 68:\penalty0 1127--1150, 2000.

S.  Hart and A.  Mas-Colell.
  A reinforcement procedure leading to correlated equilibrium.
  In Wilhelm  Neuefeind Gerard  Debreu and Walter Trockel, editors,
  \emph{Economic Essays}, pages 181--200. Springer, 2001.

E.  Lehrer.
  A wide range no-regret theorem.
  \emph{Games and Economic Behavior}, 42:\penalty0 101--115, 2003.


Gilles Stoltz and G\'{a}bor Lugosi.
  Internal regret in on-line portfolio selection.
  In \emph{COLT}, 2003.
  To appear in Machine Learning Journal.

Gilles Stoltz and G\'{a}bor Lugosi.
  Learning correlated equilibria in games with compact sets of strategies.
  submitted to Games and Economic Behavior, 2004.