The authors consider a set of W objects equipartitioned into R classes. They propose three deterministic learning automata solutions to this NP-hard problem. Although the first two are epsilon -optimal they seem to be practically feasible only when W is small. The last solution, which uses a new learning automaton, demonstrates an excellent partitioning capability. Experimentally, this solution converges an order of magnitude faster than the best known algorithm in the literature.

Additional Metadata
Conference Proceedings - COMPSAC 86: The IEEE Computer Society's Tenth Annual International Computer Software & Applications Conference.
Oommen, J, & Ma, D.C.Y. (D. C Y). (1986). FAST AUTOMATA SOLUTIONS TO THE EQUAL PARTITIONING PROBLEM. In Proceedings - IEEE Computer Society's International Computer Software & Applications Conference (pp. 358–364).