Blackwell Approachability and Minimax Theory
نویسنده
چکیده
This manuscript investigates the relationship between Blackwell Approachability, a stochastic vector-valued repeated game, and minimax theory, a single-play scalar-valued scenario. First, it is established in a general setting — one not permitting invocation of minimax theory — that Blackwell’s Approachability Theorem (Blackwell [1]) and its generalization due to Hou [6] are still valid. Second, minimax structure grants a result in the spirit of Blackwell’s weak-approachability conjecture (Blackwell [1]), later resolved by Vieille [11], that any set is either approachable by one player, or avoidable by the opponent. This analysis also reveals a strategy for the opponent.
منابع مشابه
Zero - Sum Games with Vector - Valued Payoffs
In this lecture we formulate and prove the celebrated approachability theorem of Blackwell, which extends von Neumann's minimax theorem to zero-sum games with vector-valued payoffs [1]. (The proof here is based on the presentation in [2]; a similar presentation was given by Foster and Vohra [3].) This theorem is powerful in its own right, but also has significant implications for regret minimiz...
متن کاملApproachability in infinite dimensional spaces
The approachability theorem of Blackwell (1956b) is extended to infinite dimensional spaces. Two players play a sequential game whose payoffs are random variables. A set C of random variables is said to be approachable by player 1 if he has a strategy that ensures that the difference between the average payoff and its closest point in C, almost surely converges to zero. Necessary conditions for...
متن کاملLecture : Blackwell's Approachability Theorem . Blackwell's Approachability Theorem
Counter-example to (.): If S = {(p,q) : p = q} and r(p,q) = (p,q), one can trivially, for all q, choose p(q) = q to guarantee that r(p(q),q) ∈ S. It is however not possible to find a p which works for all q, indeed the only p which works for a given q is p = q. However, the duality statement (.) holds when S is a half-space {x | v ·x ≥ c}. To see this, define a zero-sum game with scalar p...
متن کاملBlackwell Approachability and No-Regret Learning are Equivalent
We consider the celebrated Blackwell Approachability Theorem for two-player games with vector payoffs. Blackwell himself previously showed that the theorem implies the existence of a “noregret” algorithm for a simple online learning problem. We show that this relationship is in fact much stronger, that Blackwell’s result is equivalent to, in a very strong sense, the problem of regret minimizati...
متن کاملResponse-Based Approachability and its Application to Generalized No-Regret Algorithms
Approachability theory, introduced by Blackwell (1956), provides fundamental results on repeated games with vector-valued payoffs, and has been usefully applied since in the theory of learning in games and to learning algorithms in the online adversarial setup. Given a repeated game with vector payoffs, a target set S is approachable by a certain player (the agent) if he can ensure that the ave...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1110.1514 شماره
صفحات -
تاریخ انتشار 2011