It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortun...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...
Most past research work on problem subgoal ordering are of a heuristic nature and very little attempt has been made to reveal the inherent relationship between subgoal ordering co...
A constraint satisfiability problem consists of a set of variables, their associated domains (i.e., the set of values the variable can take) and a set of constraints on these vari...
based on an abstract concept of quiescence. In the following we sketch this and a related model, describe the design of our experiments, and present the results of our simulation s...
A macro-operator is an integrated operator consisting of plural primitive operators and enables a problem solver to solve more efficiently. However, if a learning system generates...