Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 7 of 7 for “"Approximate Nash equilibria"”.

  1. Computing approximate Nash equilibria

    The problem of finding equilibria in non-cooperative games and understanding their properties is a central problem in modern game theory. After John Nash proved that every finite game has at least one equilibrium (so-called Nash equilibrium), the natural question arose whether we can compute one …

    greece Repository record for Computing approximate Nash equilibria (opens in a new tab)

  2. The complexity of solution concepts in Lipschitz games

    … games with m strategies per player have pure 𝜖-approximate Nash equilibria, for 𝜖 ≥ λ√8n log(2mn). They left open, however, the question of how hard it is to find such an equilibrium. In this work, we develop an efficient reduction from more general games to Lipschitz games. We use this …

    oxford Repository record for The complexity of solution concepts in Lipschitz games (opens in a new tab)

  3. Computational Aspects of Game Theory and Microeconomics

    … the first subexponential algorithm for computing approximate Nash equilibria in $2$-player noncooperative games and extend our result to multi-player games. We further propose a second algorithm based on solving polynomial equations over the reals. Both algorithms improve the previously known …

    gatech Repository record for Computational Aspects of Game Theory and Microeconomics (opens in a new tab)

  4. STOCHASTIC OPTIMIZATION FOR DISTRIBUTED TRAINING AND MULTI-AGENT INTERACTION IN LARGE LANGUAGE MODELS

    … functions that guarantee convergence to approximate Nash equilibria; and (iv) mixture-of-tokens generation methods for reinforcement learning with verifiable feedback in LLMs.

    cornell Repository record for STOCHASTIC OPTIMIZATION FOR DISTRIBUTED TRAINING AND MULTI-AGENT INTERACTION IN LARGE LANGUAGE MODELS (opens in a new tab)

  5. Dynamic multi-person optimization with weakly coupled agents

    … The central idea behind the construction of approximate solutions is to start with the zeroth order solution (obtained by setting $\epsilon$ = 0) and iteratively obtain successively better approximations to the optimal or equilibrium solution. Specifically, we have studied LQG teams featuring …

    uiuc Repository record for Dynamic multi-person optimization with weakly coupled agents (opens in a new tab)

  6. Algorithms and complexity results for problems on fair division and imitation games

    … EFX, PO and gives a 1.067-approximation to the Nash Social Welfare (NSW) can be computed in polynomial time. We also present algorithms that satisfy a different notions of fairness, like equitability up to one good (EQ1), and equitability up to any good (EQX) along with PO in some of these …

    uiuc Repository record for Algorithms and complexity results for problems on fair division and imitation games (opens in a new tab)

  7. Δρομολόγηση και ανάθεση μήκους κύματος σε οπτικά δίκτυα

    … that the game thus defined always converges to a Nash equilibrium in a finite number of moves, and also propose algorithms for efficiently computing socially optimal and approximate Nash equilibria in specific network topologies. The price of anarchy can grow unbounded even in tree networks with …

    greece Repository record for Δρομολόγηση και ανάθεση μήκους κύματος σε οπτικά δίκτυα (opens in a new tab)