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 “"no-regret learning"”.

  1. No-Regret Learning in General Games

    This thesis investigates the regret performance of no-regret learning algorithms in the competitive, though not fully-adversarial, environment of games. We establish exponential improvements on previously best-known external and internal regret bounds for these settings. We show that Optimistic …

    mit Repository record for No-Regret Learning in General Games (opens in a new tab)

  2. Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games

    We propose efficient no-regret learning dynamics and ellipsoid-based methods for computing linear correlated equilibria—a relaxation of correlated equilibria and a strengthening of coarse correlated equilibria—in general convex games. These are games where the number of pure strategies is …

    mit Repository record for Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games (opens in a new tab)

  3. A Diagnostic and Prescriptive Conformal Prediction Framework: Applied to Sleep Disorders

    We propose a novel predictive framework for the future diagnoses and treatments of patients with neurological conditions, specifically patients with sleep disorders, given their clinical history. Via the use of a conformal algorithm with a classifier as its base model, we are able to utilize a …

    mit Repository record for A Diagnostic and Prescriptive Conformal Prediction Framework: Applied to Sleep Disorders (opens in a new tab)

  4. Theoretical Foundations for Learning in Games and Dynamic Environments

    … compute equilibria, which have the property that no agent can deviate from them and improve their utility. An additional challenge is that decisions made by agents often change the state of the environment, which is modeled as dynamic. Thus, we need efficient algorithms for learning good policies, …

    mit Repository record for Theoretical Foundations for Learning in Games and Dynamic Environments (opens in a new tab)

  5. The complexity of Nash equilibria in multiplayer zero-sum games and coordination games

    … theorem implies convexity of equilibria, polynomial-time tractability, and convergence of no-regret learning algorithms to Nash equilibria. Given that three player zero-sum games are already PPAD-complete, this class of games, i.e. with pairwise separable utility functions, defines essentially …

    mit Repository record for The complexity of Nash equilibria in multiplayer zero-sum games and coordination games (opens in a new tab)

  6. Dynamics and Phenomena in Stateful Multi-Agent Systems

    … of theoretical computer science and economics is to understand the long-run outcomes of complex processes in multi-agent systems. In many cases, such social systems are inherently algorithmic and strategic; in others, agents may act in simpler behavioral ways in response to some …

    cornell Repository record for Dynamics and Phenomena in Stateful Multi-Agent Systems (opens in a new tab)

  7. Passivity, no-regret, and performance in online learning and games

    As autonomous AI agents become more widely deployed across dynamic, multi-agent environments, they will continuously learn and interact in real time to achieve complex goals. This thesis develops a control- and game-theoretic foundation to analyze and ultimately synthesize such systems in which …

    uiuc Repository record for Passivity, no-regret, and performance in online learning and games (opens in a new tab)