Abstract: Provided is a method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning, the method including the steps of: calculating a similarity between a policy of a first agent and a policy of a second agent and computing a final reward using the similarity; and performing clustering on a replay buffer using a result of calculating the similarity between the policy of the first agent and the policy of the second agent and performing sampling on data in the cluster.

Abstract: Provided are a system and method for adaptive masking and non-directional language understanding and generation. The system for adaptive masking and non-directional language understanding and generation according to the present invention includes an encoder unit including an adaptive masking block for performing masking on training data, a language generator for restoring masked words, and an encoder for detecting whether or not the restored sentence construction words are original, and a decoder unit including a generation word position detector for detecting a position of a word to be generated next, a language generator for determining a word suitable for the corresponding position, and a non-directional training data generator for decoder training.

Abstract: Provided are a method and apparatus for online Bayesian few-shot learning. The present invention provides a method and apparatus for online Bayesian few-shot learning in which multi-domain-based online learning and few-shot learning are integrated when domains of tasks having data are sequentially given.

Abstract: A knowledge increasing method includes calculating uncertainty of knowledge obtained from a neural network using an explicit memory, determining the insufficiency of the knowledge on the basis of the calculated uncertainty, obtaining additional data (learning data) for increasing insufficient knowledge, and training the neural network by using the additional data to autonomously increase knowledge.

Abstract: The present invention provides a new learning method where regularization of a conventional model is reinforced by using an adversarial learning method. Also, a conventional method has a problem of word embedding having only a single meaning, but the present invention solves a problem of the related art by applying a self-attention model.