Efficient novelty search through deep reinforcement learning

• Main Authors: Shi, Longxiang, Li, Shijian, Zheng, Qian, Yao, Min, Pan, Gang
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Electrical and electronic engineering; Reinforcement Learning; Novelty Search
• Online Access: https://hdl.handle.net/10356/152665
• Institution: Nanyang Technological University

Novelty search, which was inspired by the nature that evolves creatures with diversity, has shown great potential in solving reinforcement learning (RL) tasks with sparse and deceptive rewards. However, most of the existing novelty search methods evolve the populations through hybrization and mutati...