SearchSkip to Search Results
- 72Artificial Intelligence
- 18Machine Learning
- 8Reinforcement Learning
- 7Computer Games
- 7Computing Science
- 4Müller, Martin
- 3Mueller, Martin
- 2Johanson, Michael
- 2Pelletier, Francis J.
- 2Schaeffer, Jonathan
- 1Adams, Cathy
- 41Graduate Studies and Research, Faculty of
- 41Graduate Studies and Research, Faculty of/Theses and Dissertations
- 18Computing Science, Department of
- 18Computing Science, Department of/Technical Reports (Computing Science)
- 3Toolkit for Grant Success
- 3WISEST Summer Research Program
Displaying believable emotional reactions in virtual characters is required in applications ranging from virtual-reality trainers to video games. Manual scripting is the most frequently used method and enables an arbitrarily high fidelity of the emotions displayed. However, scripting is labor...
The Alberta Teachers’ Association (ATA), the Kule Institute for Advanced Study (KIAS) and the Faculty of Education, University of Alberta engaged in a partnership to organize a research and policy scoping initiative that would report on the expected impact of artificial intelligence (AI) in...
Technical report TR10-04. This paper describes a novel and fast placement algorithm for field programmable gate array (FPGA) design space exploration. The proposed algorithm generates the placement based on the topological similarity between two configurations (netlists) in the design space....
Action Elimination and Plan Neighborhood Graph Search: Two Algorithms for Plan Improvement - Extended VersionDownload
Technical report TR10-01. Compared to optimal planners, satisficing planners can solve much harder problems but may produce overly costly and long plans. Plan quality for satisficing planners has become increasingly important. The most recent planning competition IPC-2008 used the cost of the...
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this...
While greedy best-first search (GBFS) is a popular algorithm for solving automated planning tasks, it can exhibit poor performance if the heuristic in use mistakenly identifies a region of the search space as promising. In such cases, the way the algorithm greedily trusts the heuristic can cause...
Reinforcement Learning is a formalism for learning by trial and error. Unfortunately, trial and error can take a long time to find a solution if the agent does not efficiently explore the behaviours available to it. Moreover, how an agent ought to explore depends on the task that the agent is...
Research in unsupervised text generation has been gaining attention over the years. One recent approach is local search towards a heuristically defined objective, which specifies language fluency, semantic meanings, and other task-specific attributes. Search in the sentence space is realized by...