Kellen Cheng, Anna Lisa Gentile, et al.
EMNLP 2024
One of the most common mechanisms used for speeding up problem solvers is macro-learning. Macros are sequences of basic operators acquired during problem solving. Macros are used by the problem solver as if they were basic operators. The major problem that macro-learning presents is the vast number of macros that are available for acquisition. Macros increase the branching factor of the search space and can severely degrade problem-solving efficiency. To make macro learning useful, a program must be selective in acquiring and utilizing macros. This paper describes a general method for selective acquisition of macros. Solvable training problems are generated in increasing order of difficulty. The only macros acquired are those that take the problem solver out of a local minimum to a better state. The utility of the method is demonstrated in several domains, including the domain of N × N sliding-tile puzzles. After learning on small puzzles, the system is able to efficiently solve puzzles of any size.
Kellen Cheng, Anna Lisa Gentile, et al.
EMNLP 2024
Amy Lin, Sujit Roy, et al.
AGU 2024
Gaku Yamamoto, Hideki Tai, et al.
AAMAS 2008
Amarachi Blessing Mbakwe, Joy Wu, et al.
NeurIPS 2023