3D points acquisitions based on robust sensors such as tactile or laser sensors are true alternatives to computer vision for 3D object recognition. In real life scenarios where robots are equipped with such sensors to acquire 3D data, only few points can be iteratively collected in a reasonable amount of time. However, existing Point-cloud classifiers are extremely sensitive to sparse points, missing parts and noise. To compensate for the sparsity of the data, some Reinforcement Learning (RL) based approaches have been proposed to learn a sparse yet efficient exploration of the target object regarding the 3D recognition objective. However, existing RL approaches only focus on classification performances to guide the training of the active acquisition-and-classification frameworks, and thus fail to dissociate poor exploration strategy (missing parts, noisy points) from actual classifier mistakes on proper data. In this study, we proposed a new RL framework that was rewarded regarding both the classification performances and the exploration quality. Our trained framework outperforms existing State-Of-The-Art models on 3D geometric objects classification. We further showed that our trained framework learnt to alternate between (1) a clean and broad exploration strategy, suitable for easily distinguishable categories, and (2) a specific local exploration strategy, facilitating the discrimination of similar categories.