Approachability of convex sets in generalized quitting games

@article{Flesch2018ApproachabilityOC,
  title={Approachability of convex sets in generalized quitting games},
  author={J{\'a}nos Flesch and Rida Laraki and Vianney Perchet},
  journal={ArXiv},
  year={2018},
  volume={abs/1609.08870}
}
CAMBRIDGE WORKING PAPERS IN ECONOMICS CAMBRIDGE-INET WORKING PAPERS Approachability with Discounting
We establish a version of Blackwell’s (1956) approachability result with discounting. Our main result shows that, for convex sets, our notion of approachability with discounting is equivalent to

References

SHOWING 1-10 OF 42 REFERENCES
Approachability of Convex Sets in Games with Partial Monitoring
We provide a necessary and sufficient condition under which a convex set is approachable in a game with partial monitoring, i.e. where players do not observe their opponents’ moves but receive random
Approachable sets of vector payoffs in stochastic games
  • E. Milman
  • Mathematics, Economics
    Games Econ. Behav.
  • 2006
Approachability, fast and slow
TLDR
A characterization for the convergence rates of approachability is provided and it is shown that in some cases a set can be approached with a 1=n rate.
An analog of the minimax theorem for vector payoffs.
for all i, j . Thus in the (two-person, zero-sum) game with matrix Λf, player I has a strategy insuring an expected gain of at least v, and player II has a strategy insuring an expected loss of at
Zero-sum repeated games: counterexamples to the existence of the asymptotic value and the conjecture maxmin=lim v(n)
We provide an example of a two-player zero-sum repeated game with public signals and perfect observation of the actions, where neither the value of the lambda-discounted game nor the value of the
Advances in Zero-Sum Dynamic Games
The Asymptotic Theory of Stochastic Games
TLDR
It is proved that limn→∞{Vn/n} = limr→0rVr, where Vn is the value of the n-stage game and Vr is thevalue of the infinite- stage game with payoffs discounted at interest rate r > 0.
Approachability, Regret and Calibration; implications and equivalences
TLDR
It is proved that approachability can be seen as a byproduct of the very existence of consistent or calibrated strategies, and a new class of intuitive algorithms, based on simple geometric properties, are exhibited.
Exponential Weight Approachability, Applications to Calibration and Regret Minimization
TLDR
Basic ideas behind the “exponential weight algorithm” (designed for aggregation or minimization of regret) can be transposed into the theory of Blackwell approachability, and an algorithm is developed bounding the distance of average vector payoffs to some product set, with a logarithmic dependency in the dimension of the ambient space.
Communication equilibrium payoffs in repeated games with imperfect monitoring
...
1
2
3
4
5
...