Search
Skip to Search Results- 9Müller, Martin (Computing Science)
- 6Schaeffer, Jonathan (Computing Science)
- 4Sturtevant, Nathan (Computing Science)
- 1Hayward, Ryan (Computing Science)
- 1Holte, Robert (Computing Science)
- 1Schuurmans, Dale (Computing Science)
- 3Artificial Intelligence
- 2Heuristic Search
- 2Monte Carlo Tree Search
- 2Reinforcement Learning
- 1Amazons
- 1BULB
-
Spring 2023
Reinforcement learning (RL) defines a general computational problem where the learner must learn to make good decisions through interactive experience. To be effective in solving this problem, the learner must be able to explore the environment, make accurate predictions about the future, and...
-
Spring 2020
In this thesis, we focus on finding efficient practical random sampling methods for time-changing discrete distributions. We empirically study ten methods including existing algorithms, and two new ones: three level search and the flat method. We review the core ideas of existing methods...
-
Fall 2023
In this thesis, we investigate applying deep learning techniques to learn the win-loss-draw results contained in the databases of the checkers-playing program CHINOOK. Our initial objectives were to (1) compare a deep-learning-based compression scheme versus the custom algorithm used in CHINOOK,...
-
Fall 2014
Heuristic search has been shown to be an effective way to solve state-space problems. While many heuristic search techniques are guaranteed to find the best solution, these are often not feasible given practical resource requirements. In such cases, it is necessary to sacrifice solution...
-
Spring 2016
This thesis proposes, analyzes and tests different exploration-based techniques in Greedy Best-First Search (GBFS) for satisficing planning. First, we show the potential of exploration-based techniques by combining GBFS and random walk exploration locally. We then conduct deep analysis on how...
-
Fall 2016
In this thesis, we investigate the move prediction problem in the game of Go by proposing a new ranking model named Factorization Bradley Terry (FBT) model. This new model considers the move prediction problem as group competitions while also taking the interaction between features into account....
-
Spring 2010
Domain-independent feature learning is a hard problem. This is reflected by lack of broad research in the area. The goal of General Game Playing (GGP) can be described as designing computer programs that can play a variety of games given only a logical game description. Any learning has to be...
-
Fall 2022
Monte Carlo Tree Search (MCTS) is an extremely successful search-based frame- work for decision making. With an accurate simulator of the environment’s dynamics, it can achieve great performance in many games and non-games applications. However, without a perfect simulator, the performance...
-
Spring 2016
This thesis applies the Monte Carlo Random Walk method (MRW) to motion planning. We explore different global and local restart strategies to improve the performance. Several new algorithms based on the MRW approach, such as bidirectional Arvand and optimizing planner Arvand*, are introduced and...
-
Fall 2011
Pinball is fast-paced arcade-style game of which the origins date back hundreds of years. Game playing robots exist for billiards, foosball, and soccer and each have their own unique challenges. The speed that balls move in pinball machines requires that players have quick reactions. We created...