Search
Skip to Search Results- 19Planning
- 6Abstractions
- 5Artificial Intelligence
- 5Heuristic Search
- 5Reinforcement Learning
- 2Game Theory
- 1Asadi Atui, Kavosh
- 1Barriga Richards, Nicolas A
- 1Brown, Jennifer A.
- 1Faid, Julian TW
- 1Fan, Gaojian
- 1Hawkin, John A
-
Fall 2009
For zero-sum games, we have efficient solution techniques. Unfortunately, there are interesting games that are too large to solve. Here, a popular approach is to solve an abstract game that models the original game. We assume that more accurate the abstract games result in stronger strategies....
-
Spring 2011
In this thesis, we study theoretically and empirically the additive abstraction-based heuristics. First we present formal general definitions for abstractions that extend to general additive abstractions. We show that the general definition makes proofs of admissibility, consistency, and...
-
Fall 2022
In this thesis, we investigate the empirical performance of several experience replay techniques. Efficient experience replay plays an important role in model-free reinforcement learning by improving sample efficiency through reusing past experience. However, replay-based methods were largely...
-
Fall 2014
An agent in an adversarial, imperfect information environment must sometimes decide whether or not to take an action and, if they take the action, must choose a parameter value associated with that action. Examples include choosing to buy or sell some amount of resources or choosing whether or...
-
Fall 2010
We investigate the use of machine learning to create effective heuristics for single-agent search. Our method aims to generate a sequence of heuristics from a given weak heuristic h{0} and a set of unlabeled training instances using a bootstrapping procedure. The training instances that can be...
-
Fall 2013
Many important problems can be cast as state-space problems. In this dissertation we study a general paradigm for solving state-space problems which we name Cluster-and-Conquer (C&C). Algorithms that follow the C&C paradigm use the concept of equivalent states to reduce the number of states...
-
Enhancements to Methods for Planning and Scheduling Fabrication Projects Utilizing Multiskilled Labour Resources
DownloadSpring 2023
In prefabrication and off-site construction, various multiskilled work crews need to be assembled to work on different workstations to process custom-designed work units, each having specific requirements for material handling, assembly connections, welding, etc. However, the frequent labour...
-
Fall 2013
Scaffolds are temporary structures that are built to support workers and materials and facilitate direct work on construction sites. A considerable amount of man power resources are consumed by industrial construction scaffolding, which makes effective planning and estimation of the same very...
-
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 2022
This thesis investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives,...