A Reinforcement Learning Model for Solving the Folding Problem

In this paper we aim at proposing a reinforcement learning based model for solving combinatorial optimization problems. Combinatorial optimization problems are hard to solve optimally, that is why any attempt to improve their solutions is beneficent. We are particularly focusing on the bidimensional protein folding problem, a well known NP-hard optimizaton problem important within many fields including bioinformatics, biochemistry, molecular biology and medicine. A reinforcement learning model is introduced for solving the problem of predicting the bidimensional structure of proteins in the hydrophobic-polar model. The model proposed in this paper can be easily extended to solve other optimization problems. We also give a mathematical validation of the proposed reinforcement learning based model, indicating this way the potential of our proposal.