Search
Skip to Search Results- 19Planning
- 5Reinforcement Learning
- 4Heuristic Search
- 3Artificial Intelligence
- 2Scheduling
- 1Abstraction
- 1Asadi Atui, Kavosh
- 1Brown, Jennifer A.
- 1Faid, Julian TW
- 1Fan, Gaojian
- 1Jabbari Arfaee, Shahab
- 1Kumar,Chandan
-
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...
-
On Efficient Planning in Large Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
DownloadFall 2023
A practical challenge in reinforcement learning is large action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly optimize a global reward function, which leads to a blow-up in the...
-
Spring 2023
AlphaZero is a self-play reinforcement learning algorithm that achieves superhuman play in the games of chess, shogi, and Go via policy iteration. To be an effective policy improvement operator, AlphaZero’s search needs to have accurate value estimates for the states that appear in its search...
-
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,...
-
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...
-
Planning for the Future of Urban Mobility: Interviews with Planning Professionals in Five Major Canadian Cities
DownloadFall 2020
Given that our urban centres have been dominated by the private car for a hundred years, this thesis asked what is next for Canadian cities. Previous research on the future of urban mobility, and specifically city planning and autonomous vehicles, has been from an American or Australian context....
-
Social Actor Engagement in Municipal Decision-Making for Parks, Planning, and Civil Society in Edmonton, Alberta, Canada 1960-2010: Institutional Intersections
DownloadSpring 2020
Edmonton, Alberta, has a unique approach to public spaces that sees conjoined creation and development sharing of public spaces for the collective benefit of the community and stakeholders; this approach began 100 years ago. Green or open spaces, natural areas, the river valley, City of Edmonton...
-
Fall 2019
In this thesis, we study merge-and-shrink (M&S), a flexible abstraction technique for generating heuristics for cost optimal planning. We first propose three novel merging strategies for M&S, namely, Undirected Min-Cut (UMC), Maximum Intermediate Abstraction Size Minimizing (MIASM), and Dynamic...
-
Fall 2018
Canada has the third largest oil reserves in the world where 97% of these reserves are located in the oil sands, Alberta province. The product resulted from the extraction of oil sands reserves is called bitumen which can be diluted and shipped to the market or it can be proceeded and upgraded...
-
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...