Strategic Learning and Its Limits

By H. Peyton Young. 2004

604 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Safety Research

View Paper: https://www.semanticscholar.org/paper/c84be78816fd8ed9fedaf4beabbb3386c60d41dd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Safety Research

Citations in the corpus

Game-Theoretic Methods for the Smart Grid: An Overview of Microgrid Systems, Demand-Side Management, and Smart Grid Communications (2012, neutral): “ng the learning process to environmental variations, among others. To address these issues several new techniques such as strategy-proof auctions or advanced learning techniques have been proposed in [6], [7]. In summary, game theory has a strong potential for addressing several emerging problems in”
Revisiting log-linear learning: Asynchrony, completeness and payoff-based implementation (2010, methodology): “A game is weakly acyclic if for any a ∈ A, there exists a better reply path starting at a and ending at some pure Nash equilibrium [32, 33].”
Simple Adaptive Strategies: From Regret-matching To Uncoupled Dynamics (2013, background): “" An additional stimulus for our research at this point was the work of Foster and Young (2003, 2006), Germano and Lugosi (2007), Kakade and Foster (2004), Young (2004, 2009).”
Constrained school choice (2009, neutral): “Young (2004) is an excellent survey of approaches to the theory of learning in games.”
Cooperative Control and Potential Games (2009, background): “A better reply path is a sequence of action proﬁles a 1 , a 2 , ..., a L such that, for every 1 ≤ (cid:96) ≤ L − 1 , there is exactly one In other words, one player moves at a time, and each time a player moves it increases its own utility.”
Prediction, learning, and games (2006, background): “The interested reader may consult the monographs of Fudenberg and Levine [119], Sorin [276], and Young [316].”
If multi-agent learning is the answer, what is the question? (2007, background): “Since that time hundreds, if not thousands, of articles have been published on the topic, and at least two books ([20] and [54]).”
A Model-Free Approach to Wind Farm Control Using Game Theoretic Methods (2013, background): “Lastly, it is worth noting that there are alternative game theoretic distributed learning algorithms that can accommodate relaxations in these assumptions while still providing provable guarantees on the system performance [27], [30], e.”
Advancing Beyond Advances in Behavioral Economics (2006, background): “Rabin and Joel Schrag (1999) and Yaariv (2005), and assume that agents miscode evidence that their prior says is unlikely? Or Rabin (2002), and assume that agents update as Bayesians but treat independent draws as draws with replacement? Or Nicholas Barberis et al.”
Regret Testing: Learning to Play Nash Equilibrium Without Knowing You Have an Opponent (2006, background): “Although q is on player 2’s grid, the definition of p in (27) does not guarantee that it is on player 1’s grid.”
Joint Strategy Fictitious Play with Inertia for Potential Games (2005, background): “This setup falls under the general subject of “learning in games” [2], [3], and there are a variety of algorithms and accompanying analysis that examine the long term behavior of these algorithms.”
Comparative evaluation of MAL algorithms in a diverse set of ad hoc team problems (2012, background): “In such a setting, the environment is inherently nonstationary [37] and the interactive behaviour needs more careful treatment.”