Search
Skip to Search Results- 83Reinforcement Learning
- 82Artificial Intelligence
- 34Machine Learning
- 12Planning
- 7Computer Games
- 7Computing Science
- 116Graduate and Postdoctoral Studies (GPS), Faculty of
- 116Graduate and Postdoctoral Studies (GPS), Faculty of /Theses and Dissertations
- 23Computing Science, Department of
- 23Computing Science, Department of/Technical Reports (Computing Science)
- 4WISEST Summer Research Program
- 4WISEST Summer Research Program/WISEST Research Posters
-
1991
Pelletier, Francis J., Schubert, Lenhart
Introduction: This very short book is apparently intended as a supplementary text in a graduate AI course. The author describes it as a \"text and reference work on the applications of non-standard logics to artificial intelligence (AI).\" It gives short and concise (too short and too concise, in...
-
1992
Technical report TR92-19. In August 1992, the first man versus machine world championship took place. The champion, Dr. Marion Tinsley, is arguably the greatest checkers player that ever lived. The challenger was the computer checkers program Chinook, a 3 year team effort from the University of...
-
[Review of the book Formal Methods in Artificial Intelligence, by Aamsay]
1996
Introduction: Many universities teach artificial intelligence (AI) by having one undergraduate course that introduces students to a very wide variety of topics, usually including search and search heuristics, representational systems (including formal logic), problem solving, vision, expert...
-
2002
Fortin, David, Antoniu, Angela, Sardarli, Arzu, Rezania, Vahid, Levner, Ilya, Bulitko, Vadim
Technical report TR02-14. The 2002 Quantum Computing Summer School (QCSS'02) at the University of Alberta was organized as a learning and discussion forum for researchers in Artificial Intelligence, Computer Science, Physics, Mathematics, and Engineering. The short-term objective was to introduce...
-
2006
Wang, Tao, Schuurmans, Dale, Bowling, Michael
Technical report TR06-26. We investigate the dual approach to dynamic programming and reinforcement learning, based on maintaining an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit...
-
2007
Wang, Tao, Schuurmans, Dale, Bowling, Michael, Lizotte, Daniel
Technical report TR07-05. We investigate novel, dual algorithms for dynamic programming and reinforcement learning, based on maintaining explicit representations of stationary distributions instead of value functions. In particular, we investigate the convergence properties of standard dynamic...
-
2008
Lizotte, Daniel, Wang, Tao, Bowling, Michael, Schuurmans, Dale
Technical report TR08-16. We propose a dual approach to dynamic programming and reinforcement learning based on maintaining an explicit representation of visit distributions as opposed to value functions. An advantage of working in the dual is that it allows one to exploit techniques for...
-
2008
Niewiadomski, Robert, Amaral, Jose Nelson, Holte, Robert
Technical report TR08-18. We present an advanced Bidirectional A* algorithm featuring an application of Frontier Search and a strategy for the performance-efficient utilization of External Memory. We present the results of an experimental evaluation demonstrating that this algorithm is capable of...