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 17 of 17 for “"Learning in games"”.
-
Algorithmic learning in games
This dissertation studies algorithmic agents that interact repeatedly in strategic settings. Chapter 2 provides asymptotic results for a family of reinforcement learning algorithms known as ‘actor-critic learners’. Each such algorithmic agent simultaneously estimates what is called a ‘critic’, such …
-
Distributed dynamics and learning in games
<p>In this thesis we study decentralized dynamics for non-cooperative and cooperative games. The dynamics are behaviorally motivated and assume that very little information is available about other players' preferences, actions, or payoffs. For example, this is the case in markets where exchanges …
-
Social norms and learning in games
<p><b>Duelling</b></p> <p>The norm of duelling endured for hundreds of years in Europe. In the United Kingdom it disappeared abruptly in the mid-nineteenth century, whereas in France it declined slowly. I present a simple model of social norms that explains these phenomena. The model predicts that …
-
Distributed learning in games under bounded rationality
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01
-
Convergence to Nash in the potential Linear Quadratic games and accelerated learning in games
Game theory and online optimization have a close relationship with each other. In some literature, online optimization has been employed for solving game theory problems. Many accelerated algorithms are proposed for offline optimization problems. However, to the best of our knowledge, there is not …
-
Evaluating social and cognitive effects of video games using electroencephalography.
Games User Research (GUR) is an area of evaluative player research and human-computer interaction (HCI) that aims to improve games, focused on a player’s understanding and on their experience when playing games. In this field, techniques are available to measure and understand user experience. …
-
Higher-order learning in finite games
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01
-
Reinforcement Learning for Decentralized Stochastic Control
… of a controlled stochastic system where a finite number of decision makers seek to arrive at optimal policies using only local measurements and cost realizations. For such a context, a recent result in the literature established convergence to person-by-person-optimal policies (and a class …
-
LEARNING, GAMES AND OPTIMALITY: ALGORITHMS FOR DECISION-MAKING IN COMPLEX ENVIRONMENTS
This thesis investigates algorithms for environments where nuanced, multidimensional objectives are necessary, either due to the presence of strategic agents or due to fine-grained requirements. A central question we address is what kind of algorithm should be employed to play a repeated game …
-
Level Up: Supporting In-Game Skill Development
Video games are challenging and complex. They require players to master a diverse set of skills to succeed. Through play, players acquire and eventually master these skills, transitioning from novice to expert through skill development. Making progress and performing well in a game is directly tied …
-
Games of Private Information and Learning
<p>This dissertation studies private information and learning in games. Chapter 1 considers a dynamic game of strategic adoption, in which a patient buyer faces a seller of privately known quality. The buyer learns about the seller gradually through an exogenous news process, and the seller is able …
-
Game-theoretic methods for security and resilience in cyber-physical systems
Modern critical infrastructures are highly integrated systems composed of many complex interactions between different system modules or agents including cyber and physical components as well as human factors. Their growing complexity demands novel design techniques for scalable and efficient …
-
Dynamics and Phenomena in Stateful Multi-Agent Systems
An important goal at the intersection 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 …
-
Learning in Engineered Multi-agent Systems
Consider the problem of maximizing the total power produced by a wind farm. Due to aerodynamic interactions between wind turbines, each turbine maximizing its individual power--as is the case in present-day wind farms--does not lead to optimal farm-level power capture. Further, there are no good …
-
Distributed learning in large populations
Distributed learning is the iterative process of decision-making in the presence of other decision-makers. In recent years, researchers across fields as disparate as engineering, biology, and economics have identified mathematically congruous problem formulations at the intersection of their …