An important feature of many problem domains in machine learning is their geometry. For example, adjacency relationships, symmetries, and Cartesian coordinates are essential to an...
In designing Markov Decision Processes (MDP), one must define the world, its dynamics, a set of actions, and a reward function. MDPs are often applied in situations where there i...
David L. Roberts, Sooraj Bhat, Kenneth St. Clair, ...
Various problems in AI and multiagent systems can be tackled by finding the “most desirable” elements of a set given some binary relation. Examples can be found in areas as d...
Depth-first proof-number search (df-pn) is powerful AND/OR tree search to solve positions in games. However, df-pn has a notorious problem of infinite loops when applied to domain...
We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on ac...
Kshitij Judah, Saikat Roy, Alan Fern, Thomas G. Di...