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 20 of 24 for “"Potential Games"”.

  1. Economic applications of potential games

    … The dissertation shows how the utilization of potential game theory can better deal with this challenge. Chapter 1 studies a general contracting problem between one principal and multiple agents. The interdependence of agents’ actions and payoffs creates a coordination problem among them, …

    bu Repository record for Economic applications of potential games (opens in a new tab)

  2. Multi-Robot Exploration Using Potential Games

    … multiple robots by modelling the problem as a Potential Game rather than using conventional frontier-based dynamic programming algorithms. A potential game is a type of game that results in coordinated behaviours amongst players. This is done by enforcing strict rules for each player in …

    carleton Repository record for Multi-Robot Exploration Using Potential Games (opens in a new tab)

  3. Evolutionary Markov chains, potential games and optimization under the lens of dynamical systems

    … or even the behavior of rational agents in potential games. The mathematical equations that describe the evolution of such systems are continuous or discrete dynamical systems (in particular they can be Markov chains). The challenging part in the analysis of these systems is that they live …

    gatech Repository record for Evolutionary Markov chains, potential games and optimization under the lens of dynamical systems (opens in a new tab)

  4. Convergence to Nash in the potential Linear Quadratic games and accelerated learning in games

    … Nash, with a fast convergence rate in Cournot games and Quadratic games. It is desired that this online algorithm also minimize the regret of a sequence of functions for both zero-order and first-order feedback. In potential Linear Quadratic (LQ) games, we also study the convergence of the …

    ubc Repository record for Convergence to Nash in the potential Linear Quadratic games and accelerated learning in games (opens in a new tab) Download PDF for Convergence to Nash in the potential Linear Quadratic games and accelerated learning in games (opens in a new tab)

  5. Potential game based cooperative control in dynamic environments

    … to extend cooperative control methods based on potential games to dynamic environments and to develop an experimental test bed to illustrate theoretical results. Cooperative control concerns coordinating a collective performance of multiple autonomous agents. Possible applications include mobile …

    gatech Repository record for Potential game based cooperative control in dynamic environments (opens in a new tab)

  6. Information Diffusion on Social Networks

    … cliques and trees. We give some results on potential games on the iterated local transitivity model. Chapter 2 provides an introduction to graph properties, and describes various early graph models. Chapter 3 describes some models for online social networks, and introduces the iterated local …

    maynooth Download PDF for Information Diffusion on Social Networks (opens in a new tab)

  7. Networked Game-Theoretical Learning in Autonomous Systems

    … to pure Nash equilibria in weakly-acyclic games while reducing communication attempts. We verify the effectiveness of the proposed communication protocols on mobile autonomous teams solving the target assignment problem. The second part of the thesis considers the analysis of multi-agent …

    tamu Repository record for Networked Game-Theoretical Learning in Autonomous Systems (opens in a new tab)

  8. Adaptive Reconfiguration of Protection Relays to Accommodate Distributed

    … with DGs. Through theoretical studies based on potential games and practical simulations, the OC relays' settings are reconfigured to adapt to the DN's changes in the system as a result of DG integration.

    york Repository record for Adaptive Reconfiguration of Protection Relays to Accommodate Distributed (opens in a new tab)

  9. DYNAMIC GAMES AND GAMES WITH MANY PLAYERS

    … introduce two widely used models in game theory: games with many players (large games) and dynamic games with perfect information. In the game with many players, each player's payoff depends on her own action and the distribution of the other players' actions, and this model can be applied to many …

    nus Repository record for DYNAMIC GAMES AND GAMES WITH MANY PLAYERS (opens in a new tab) Download file for DYNAMIC GAMES AND GAMES WITH MANY PLAYERS (opens in a new tab)

  10. Nash, Stackelberg and hybrid games : studies for game-theoretic control of autonomous vehicles

    … the AV decision-making problem. Two classes of games, including Nash game and Stackelberg games, are developed respectively. For each of the two games, two solution settings, including pairwise games and multi-player games, are introduced, respectively, to solve the game in multi-agent …

    missouri Repository record for Nash, Stackelberg and hybrid games : studies for game-theoretic control of autonomous vehicles (opens in a new tab)

  11. Βελτιστοποίηση των μηχανισμών πολλαπλής πρόσβασης και της ενεργειακής αυτονομίας σε ασύρματα δίκτυα αισθητήρων με βάση τη θεωρία παιγνίων

    … quality optimisation problems as non-cooperative Potential Games. This class of games can be solved in a distributed fashion. We investigate power and topology control, as well as end-to-end throughput optimisation with convex and non-convex utilities and different properties in the strategy sets. …

    greece Repository record for Βελτιστοποίηση των μηχανισμών πολλαπλής πρόσβασης και της ενεργειακής αυτονομίας σε ασύρματα δίκτυα αισθητήρων με βάση τη θεωρία παιγνίων (opens in a new tab)

  12. Βελτιστοποίηση ασύρματων κυψελωτών δικτύων με υποστήριξη άμεσης επικοινωνίας

    … The first problem is modelled as an exact potential game where the total interference of the network coincides the opposite of the potential function of the respective game. Leveraging the desirable properties of the exact potential games a best response algorithm is proposed which …

    greece Repository record for Βελτιστοποίηση ασύρματων κυψελωτών δικτύων με υποστήριξη άμεσης επικοινωνίας (opens in a new tab)

  13. GAME THEORETIC APPROACHES TO PETROLEUM REFINERY PRODUCTION PLANNING – A JUSTIFICATION FOR THE ENTERPRISE LEVEL OPTIMIZATION OF PRODUCTION PLANNING

    … formulated problems, which are reformulated into potential games. Nonlinear programming potential game frameworks are developed for static and dynamic production planning problems, as well for mixed integer nonlinear expansion planning problems in which refiners have access to potential upgrades …

    mcmaster Repository record for GAME THEORETIC APPROACHES TO PETROLEUM REFINERY PRODUCTION PLANNING – A JUSTIFICATION FOR THE ENTERPRISE LEVEL OPTIMIZATION OF PRODUCTION PLANNING (opens in a new tab)

  14. Exploiting Structures in Reinforcement Learning: Multi-Agent Homogeneity, Euclidean Symmetry, and Natural Languages

    … actor-critic methods for homogeneous Markov games, enabling scalable learning with reduced coordination overhead. Second, we introduce Euclidean symmetry in RL, demonstrating how equivariant function approximators can significantly enhance sample efficiency and generalization in spatially …

    south-carolina Repository record for Exploiting Structures in Reinforcement Learning: Multi-Agent Homogeneity, Euclidean Symmetry, and Natural Languages (opens in a new tab)

  15. Multi-Agent Mechanisms and Learning in Energy Applications

    … that we study two classes of multi-agent dynamic games, namely Mean Field Games (MFG) and Markov Potential Games (MPG). MFG framework is a promising approach when systems involve a large number of agents, and the framework gets more accurate as the number of agents grows. MPG framework is a class …

    tamu Repository record for Multi-Agent Mechanisms and Learning in Energy Applications (opens in a new tab)

  16. Efficient Algorithm for Learning and Generation with Reinforcement Learning

    … theoretical framework for average reward Markov potential games, establishing the smoothness of average reward functions and introducing three independent learning algorithms-policy gradient, proximal-Q, and natural policy gradient--with provable convergence to Nash equilibria. Our analysis …

    tamu Repository record for Efficient Algorithm for Learning and Generation with Reinforcement Learning (opens in a new tab) Embargoed until 2028-05-01

  17. Efficient Algorithm for Learning and Generation with Reinforcement Learning

    … theoretical framework for average reward Markov potential games, establishing the smoothness of average reward functions and introducing three independent learning algorithms-policy gradient, proximal-Q, and natural policy gradient--with provable convergence to Nash equilibria. Our analysis …

    tamu Repository record for Efficient Algorithm for Learning and Generation with Reinforcement Learning (opens in a new tab) Embargoed until 2028-05-01

  18. Preference Games and Sink Equilibria

    … graph, a natural object underlying all classical games. We call this model a preference game. Preference games generalise classical games in that all classical games have an associated preference game. Preference games also have a natural choice of solution concept: the sink equilibria, which are …

    anu Repository record for Preference Games and Sink Equilibria (opens in a new tab)

Page 1 of 2