Reinforced random forest

Reinforcement learning improves classification accuracy. But use of reinforcement learning is relatively unexplored in case of random forest classifier. We propose a reinforced random forest (RRF) classifier that exploits reinforcement learning to improve classification accuracy. Our algorithm is initialized with a forest. Then the entire training data is tested using the initial forest. In order to reinforce learning, we use mis-classified data points to grow certain number of new trees. A subset of the new trees is added to the existing forest using a novel graph-based approach. We show that addition of these trees ensures improvement in classification accuracy. This process is continued iteratively until classification accuracy saturates. The proposed RRF has low computational burden. We achieve at least 3% improvement in F-measure compared to random forest in three breast cancer datasets. Results on benchmark datasets show significant reduction in average classification error.