Search
Skip to Search Results- 21Game theory
- 6Poker
- 4Regret minimization
- 3Computer Games
- 3Machine learning
- 2Artificial Intelligence
- 3Johanson, Michael
- 2Bowling, Michael
- 2Lanctot, Marc
- 2Zinkevich, Martin
- 1Ajallooeian, Mohammad Mahdi
- 1Bernard, Benjamin
- 15Graduate and Postdoctoral Studies (GPS), Faculty of
- 15Graduate and Postdoctoral Studies (GPS), Faculty of/Theses and Dissertations
- 5Computing Science, Department of
- 5Computing Science, Department of/Technical Reports (Computing Science)
- 1Biological Sciences, Department of
- 1Biological Sciences, Department of/Journal Articles (Biological Sciences)
-
Fall 2023
Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that agents the learner will face post-training may have...
-
Modelling phytoplankton across many scales: transient dynamics, human interactions, and niche differentiation in the light spectrum
DownloadFall 2021
In recent decades freshwater lakes have seen an increase in human presence. A common byproduct of this human presence is anthropogenic nutrient pollution resulting in eutrophication, a term that is becoming all too synonymous with harmful algal blooms. It is well known that phytoplankton...
-
Spring 2018
Decision-making problems with two agents can be modeled as two player games, and a Nash equilibrium is the basic solution concept describing good play in adversarial games. Computing this equilibrium solution for imperfect information games, where players have private, hidden information, is...
-
Continuous-time Repeated Games with Imperfect Information: Folk Theorems and Explicit Results
DownloadSpring 2016
This thesis treats continuous-time models of repeated interactions with imperfect public monitoring. In such models, players do not directly observe each other's actions and instead see only the impacts of the chosen actions on the distribution of a random signal. Often, there are two reasons why...
-
Regret Minimization in Games and the Development of Champion Multiplayer Computer Poker-Playing Agents
DownloadSpring 2014
Recently, poker has emerged as a popular domain for investigating decision problems under conditions of uncertainty. Unlike traditional games such as checkers and chess, poker exhibits imperfect information, varying utilities, and stochastic events. Because of these complications, decisions at...
-
Spring 2014
Cooperative system is a promising concept to improve the performance of the communication in wireless networks. This new paradigm of wireless communication imposes new challenges to traditional problems such as resource allocation. To model the behaviors of selfish and autonomous nodes in a...
-
Efficiency and Security Analysis in Multi-User Wireless Communication Systems: Cooperation, Competition and Malicious Behavior
DownloadSpring 2014
Efficiency and security are major concerns with increasingly higher importance in modern wireless communications. These two concerns are especially significant for multi-user wireless communications where different users share or compete for resources. Among different users, there are...
-
2013
In the field of computational game theory, games are often compared in terms of their size. This can be measured in several ways, including the number of unique game states, the number of decision points, and the total number of legal actions over all decision points. These numbers are either...
-
2013-02-26
In the field of computational game theory, games are often compared in terms of their size. This can be measured in several ways, including the number of unique game states, the number of decision points, and the total number of legal actions over all decision points. These numbers are either...
-
Monte Carlo Sampling and Regret Minimization for Equilibrium Computation and Decision-Making in Large Extensive Form Games
DownloadSpring 2013
In this thesis, we investigate the problem of decision-making in large two-player zero-sum games using Monte Carlo sampling and regret minimization methods. We demonstrate four major contributions. The first is Monte Carlo Counterfactual Regret Minimization (MCCFR): a generic family of...