Research Article Open Access

Exploring Learning Capability of an Agent in SOAR: Using 8-Queens Problem

Neha Rajan1 and Sunderrajan Srinivasan2
  • 1 Mewar University, India
  • 2 PDM University, India
Journal of Computer Science
Volume 16 No. 5, 2020, 642-650

DOI: https://doi.org/10.3844/jcssp.2020.642.650

Submitted On: 4 November 2019 Published On: 25 May 2020

How to Cite: Rajan, N. & Srinivasan, S. (2020). Exploring Learning Capability of an Agent in SOAR: Using 8-Queens Problem. Journal of Computer Science, 16(5), 642-650. https://doi.org/10.3844/jcssp.2020.642.650

Abstract

Cognitive architecture deals with describing the intelligent behavior of an agent. The description of intelligent behavior states how well an agent can solve and represent variety of problems of the domain-independent task. The intelligence of an agent is considered in terms of its learning capabilities. In this study, we are exploring solving 8-Queens combinatorial problem using SOAR symbolic cognitive architecture. An 8-Queens problem consists of various constraints which is expressed by Constraint Satisfaction Problem (CSP). The constraints are further generalized in the Fuzzy Constraint Satisfaction Problem (FCSP) (a sub domain of CSP), which simplifies the condition of constraints by providing the priority value to the location of queen. This paper provides a way to solve 8-Queens problem by using a heuristic search and backtracking. These concepts are implemented in SOAR to find an efficient solution of similar task. The implementation of 8-Queens in SOAR provides computation efficiency in solving and a way for an agent to learn their own production rules to solve similar domain problems. The 8-Queens problem is analyzed by two parameters. First parameter defines how an agent can learn and transfer rules to solve similar domain problem. The second parameter describes number of chunks required to solve a problem.

  • 353 Views
  • 93 Downloads
  • 0 Citations

Download

Keywords

  • Procedural Memory
  • Chunking
  • Constraint Satisfaction Problem
  • Backtracking