TY - JOUR
T1 - Probabilistic incremental program evolution
AU - Salustowicz, Rafal
AU - Schmidhuber, Jürgen
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 1997/1/1
Y1 - 1997/1/1
N2 - Probabilistic incremental program evolution (PIPE) is a novel technique for automatic program synthesis. We combine probability vector coding of program instructions, population-based incremental learning, and tree-coded programs like those used in some variants of genetic programming (GP). PIPE iteratively generates successive populations of functional programs according to an adaptive probability distribution over all possible programs. Each iteration, it uses the best program to refine the distribution. Thus, it stochastically generates better and better programs. Since distribution refinements depend only on the best program of the current population, PIPE can evaluate program populations efficiently when the goal is to discover a program with minimal runtime. We compare PIPE to GP on a function regression problem and the 6-bit parity problem. We also use PIPE to solve tasks in partially observable mazes, where the best programs have minimal runtime. © 1997 by the Massachusetts Institute of Technology.
AB - Probabilistic incremental program evolution (PIPE) is a novel technique for automatic program synthesis. We combine probability vector coding of program instructions, population-based incremental learning, and tree-coded programs like those used in some variants of genetic programming (GP). PIPE iteratively generates successive populations of functional programs according to an adaptive probability distribution over all possible programs. Each iteration, it uses the best program to refine the distribution. Thus, it stochastically generates better and better programs. Since distribution refinements depend only on the best program of the current population, PIPE can evaluate program populations efficiently when the goal is to discover a program with minimal runtime. We compare PIPE to GP on a function regression problem and the 6-bit parity problem. We also use PIPE to solve tasks in partially observable mazes, where the best programs have minimal runtime. © 1997 by the Massachusetts Institute of Technology.
UR - https://direct.mit.edu/evco/article/5/2/123-141/789
UR - http://www.scopus.com/inward/record.url?scp=0000108169&partnerID=8YFLogxK
U2 - 10.1162/evco.1997.5.2.123
DO - 10.1162/evco.1997.5.2.123
M3 - Article
SN - 1063-6560
VL - 5
SP - 123
EP - 141
JO - Evolutionary Computation
JF - Evolutionary Computation
IS - 2
ER -