MCTS guided Genetic Algorithm for optimization of neural network weights

TL;DR

This paper proposes combining Monte Carlo Tree Search with genetic algorithms to efficiently optimize neural network weights, aiming to improve search speed and solution quality.

Contribution

It introduces a novel hybrid approach integrating MCTS with GA for neural network optimization, enhancing search efficiency over traditional methods.

Findings

MCTS-guided GA outperforms standard GA in convergence speed.

The hybrid method finds better neural network weights with fewer evaluations.

Results demonstrate improved optimization quality and computational efficiency.

Abstract

In this research, we investigate the possibility of applying a search strategy to genetic algorithms to explore the entire genetic tree structure. Several methods aid in performing tree searches; however, simpler algorithms such as breadth-first, depth-first, and iterative techniques are computation-heavy and often result in a long execution time. Adversarial techniques are often the preferred mechanism when performing a probabilistic search, yielding optimal results more quickly. The problem we are trying to tackle in this paper is the optimization of neural networks using genetic algorithms. Genetic algorithms (GA) form a tree of possible states and provide a mechanism for rewards via the fitness function. Monte Carlo Tree Search (MCTS) has proven to be an effective tree search strategy given states and rewards; therefore, we will combine these approaches to optimally search for the best result generated with genetic algorithms.