AUTOMATIC ALGORITHM DEVELOPMENT USING NEW REINFORCEMENT PROGRAMMING TECHNIQUES

作者：White Spencer; Martinez Tony; Rudolph George^*

来源：Computational Intelligence, 2012, 28(2): 176-208.

DOI：10.1111/j.1467-8640.2012.00413.x

• reinforcement programming
• genetic programming
• reinforcement learning
• automatic code generation
• state representation

Reinforcement Programming (RP) is a new approach to automatically generating algorithms that uses reinforcement learning techniques. This paper introduces the RP approach and demonstrates its use to generate a generalized, in-place, iterative sort algorithm. The RP approach improves on earlier results that use genetic programming (GP). The resulting algorithm is a novel algorithm that is more efficient than comparable sorting routines. RP learns the sort in fewer iterations than GP and with fewer resources. Experiments establish interesting empirical bounds on learning the sort algorithm: A list of size 4 is sufficient to learn the generalized sort algorithm. The training set only requires one element and learning took less than 200,000 iterations. Additionally RP was used to generate three binary addition algorithms: a full adder, a binary incrementer, and a binary adder.

• 出版日期2012-5