Electronics and Telecommunications Research Institute

Byung Hyun Yoo

Hyun Woo Kim

Hwa Jeon Song

Jeon Gue Park

Eui Sok Chung

Sungwon Yi

Yoo Rhee Oh

Ran Han

Ningombam Devarani Devi

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.

Method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning

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.

Method and apparatus of increasing knowledge based on uncertainty in neural networks

Growing community of inventors

Daejeon, South Korea

Byung Hyun Yoo