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 64 for “"Stochastic Games"”.
-
Algorithms for Simple Stochastic Games
A simple stochastic game (SSG) is a game defined on a directed multigraph and played between players MAX and MIN. Both players have control over disjoint subsets of vertices: player MAX controls a subset VMAX and player MIN controls a subset VMIN of vertices. The remaining vertices fall into either …
-
Stochastic games and monotone comparative statics
… 3, I analyse a new class of dynamic public-good games arising among innovators of a common technology who share improvements with one other. Innovators could be firms part of an R&D; alliance or an informal disclosure agreement. The game is novel as firms induce randomly-sized increments in the …
-
Some problems in discounted stochastic games
… three problems in the theory of iscounted stochastic games, all motivated by the effects of time-dependent dis-counting. First, it investigates the Nash equilibrium of finite stochastic games with generalised discounting. By employing the framework of gener-alised continuous games, it is …
-
Empirical-evidence equilibria in stochastic games
… of empirical-evidence equilibria (EEEs) in stochastic games. This framework was developed while attempting to design decentralized controllers using learning in stochastic games. The overarching goal is to enable a set of agents to control a dynamical system in a decentralized fashion. To do …
-
Assume-guarantee strategy synthesis for stochastic games
… model systems as turn-based two-player zero-sum stochastic games, which are able to express both stochastic and nondeterministic environmental uncertainty. Given a system model and a specification, we define the strategy synthesis problem as that of finding a strategy for the system that is …
-
Essays on Computational Frameworks for Stochastic Games
… focuses on algorithmic solution methods for stochastic games. It tests the reliability of algorithms for equilibrium analysis through simulations against calculable analytical benchmarks, and examines the performance of algorithms beyond the classes of games for which they were originally …
-
An Empirical Analysis of Algorithms for Simple Stochastic Games
… a computational study on algorithms for Simple Stochastic Games (SSG). Simple Stochastic Games are a restriction of the Shapley stochastic model motivated by their applications in AI planning, logic synthesis, and theoretical computer science. This thesis seeks to empirically assess the …
-
Learning Average Reward Irreducible Stochastic Games: Analysis and Applications
… decision makers/agents can be modeled as stochastic games. Stochastic games having Markov properties are called Markov games or competitive Markov decision processes. This dissertation presents an approach to solve non cooperative stochastic games, in which each decision maker makes …
-
On stochastic games, reinforcement learning, and platform competition and collusion
… with bounded experimentation in a setting of stochastic games with bounded memory and show sufficient conditions under which firms learn that charging supracompetitive prices is optimal in the long run. We also show sufficient conditions for these supracompetitive prices to be supported by …
-
Value methods for efficiently solving stochastic games of complete and incomplete information
… these models. We tackle three well known models: stochastic games, decentralized partially observable Markov decision problems, and partially observable stochastic games. We also present a new fourth model, Markov games of incomplete information, to help solve the partially observable models. For …
-
Comparison and Continuity Properties of Equilibrium Values in Information Structures for Stochastic Games
In stochastic games where players measure a cost-relevant exogenous state variable through measurement channels, an information structure is the joint probability measure induced on the state space and player measurement spaces. For single-player decision problems in finite spaces, a theorem due to …
-
Learning Nash equilibria in zero-sum stochastic games via entropy-regularized policy approximation
… We propose a new algorithm for zero-sum stochastic games in which each agent simultaneously learns a Nash policy and an entropy-regularized policy.The two policies help each other towards convergence: the former guides the latter to the desired Nash equilibrium, and the latter serves as …
-
Automatic verification and strategy synthesis for zero-sum and equilibria properties of concurrent stochastic games
… presenting a framework for verifying concurrent stochastic systems, where agents may compete or cooperate. More specifically, we model systems as concurrent multi-player stochastic games, which are mathematical models able to express environmental uncertainty, nondeterminism and, at each step, …
-
Structural Estimation of Partially Observable Markov Decision Processes and Partially Observable Stochastic Games: Theory and Applications
… for single agent) and partially observable stochastic game (POSG, for multiple agents) are two well-known classes of models that study the optimal decision making of a rational agent under uncertainty, where the state of the world is hidden and can only be related to noisy observations. In …
-
Theory of Correspondences and Games
In this thesis, we will consider games with large structures in the sense that the player/state space can be uncountable. We propose an appropriate condition called ?setwise coarseness? and prove several regularity properties (convexity, compactness and preservation of upper hemicontinuity) of …
-
Several Reinforcement Learning Methods in Mean-Field Games with Binary Action Spaces
… will be used to study binary action space stochastic games with a sufficiently large number of players that can be generalized to the multi-population case. Based on the mean-field approximation, several algorithms will be implemented and compared in numerical experiments to visualize their …
-
Algorithmic Trading with Latent Models and Mean-Field Games
… the problem from the perspective of large-scale stochastic games with incomplete information and populations composed of heterogeneous agents, to which it provides closed form and model-agnostic solutions. The thesis contains two main parts. In the first part, we study the single agent optimal …
-
Toward Assured Autonomy with Model-Free Reinforcement Learning
… obtain controllers for AS operating in unknown, stochastic, and potentially adversarial environments directly from linear temporal logic (LTL) specifications defined on state labels, such as safety and liveness requirements. This ensures that the learned controllers satisfy the desired …
-
Unifying Strategic Military Force Design and Operational Warfighting: A Stochastic Game Approach
… a framework to unify these levels through stochastic games and a force design model. We start with the operational level, where we exploit the structure of military games to construct a tractable representation of the large-scale problem. We develop the campaign stochastic game (CSG), a …
Page 1 of 4