Modern deep reinforcement learning (DRL) has been successful in solving a range of challenging sequential decision-making problems. Most of these algorithms use an ensemble of neural networks as their backbone structure and benefit from the diversity among the neural networks to achieve optimal results. Unfortunately, the members of the ensemble can converge to the same point either the parametric space or representation space during the training phase, therefore, losing all the leverage of an ensemble. In this paper, we describe Maximize Ensemble Diversity in Reinforcement Learning (MED-RL), a set of regularization methods inspired from the economics and consensus optimization to improve diversity in the ensemble-based deep reinforcement learning methods by encouraging inequality between the networks during training. We integrated MED-RL in five of the most common ensemble-based deep RL algorithms for both continuous and discrete control tasks and evaluated on six Mujoco environments and six Atari games. Our results show that MED-RL augmented algorithms outperform their un-regularized counterparts significantly and in some cases achieved more than 300$\%$ in performance gains.