Speedup learning is a branch of machine learning that studies learning mechanisms for speeding up problem solvers based on problem-solving experience. The input to a speedup learner typically consists of observations of prior problem-solving experience, which may include traces of the problem solver’s operations and/or solutions to solve the problems. The output is knowledge that the problem solver can exploit to find solutions more quickly than before learning without seriously effecting the solution quality. The most distinctive feature of speedup learning, compared with most branches of machine learning, is that the learned knowledge does not provide the problem solver with the ability to solve new problem instances. Rather, the learned knowledge is intended solely to facilitate faster solution times compared to the solver without the knowledge.
Motivation and Background
Much of the work in computer science and especially artificial intelligence aims at developing...
- Boyan, J. A., & Moore, A. W. (1998). Learning evaluation functions for global optimization and boolean satisfiability. In National conference on artificial intelligence (pp. 3–10). Mlenio Park, CA: AAAI Press.Google Scholar
- Huang, Y.-C., Selman, B., & Kautz, H. (2000). Learning declarative control rules for constraint-based planning. In International conference on machine learning (pp. 415–422). San Francisco: Morgan Kaufmann.Google Scholar
- Minton, S. (1988). Quantitative results concerning the utility of explanation-based learning. In National conference on artificial intelligence (pp. 564–569). St. Paul, MN: Morgan Kaufmann.Google Scholar
- Minton, S. (Ed.) (1993). Machine learning methods for planning. San Francisco: Morgan Kaufmann.Google Scholar
- Sarkar, S., Chakrabarti, P., & Ghose, S. (1998). Learning whiles solving problems in best first search. IEEE Transactions on Systems, Man, and Cybernetics–Part A: Systems and Humans, 28(4), 553–541.Google Scholar
- Zimmerman, T., & Kambhampati, S. (2003). Learning-assisted automated planning: Looking back, taking stock, going forward. AI Magazine, 24(2), 73–96.Google Scholar