19250

Video URL

https://simons.berkeley.edu/talks/learning-solution-concept-part-i

Learning as a Solution Concept (Part I)

(2022). Learning as a Solution Concept (Part I). The Simons Institute for the Theory of Computing. https://simons.berkeley.edu/talks/learning-solution-concept-part-i

Learning as a Solution Concept (Part I). The Simons Institute for the Theory of Computing, Jan. 24, 2022, https://simons.berkeley.edu/talks/learning-solution-concept-part-i 

          @misc{ scivideos_19250,
            doi = {},
            url = {https://simons.berkeley.edu/talks/learning-solution-concept-part-i},
            author = {},
            keywords = {},
            language = {en},
            title = {Learning as a Solution Concept (Part I)},
            publisher = {The Simons Institute for the Theory of Computing},
            year = {2022},
            month = {jan},
            note = {19250 see, \url{https://scivideos.org/Simons-Institute/19250}}
          }
Éva Tardos (Cornell University)
Talk number19250
Source RepositorySimons Institute
Subject

Abstract

In over the last two decades we have developed good understanding how to quantify the impact of strategic user behavior on overall performance in many games (including traffic routing as well as online auctions). Early work focused on evaluating the quality of Nash equilibria. However, it turns out that the resulting bounds extend to learning out comes in repeated games under pretty general assumptions. In this talk we will review these results, which mostly assume that learners satisfy versions of the no-regret property after a long enough play. We will also discuss pros and cons of no-regret as a behavioral assumption on learning outcomes, as well as limitations of assuming no-regret as the main condition players achieve as they are learning.