Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth Stanley, Jeff Clune

Nov-18-2025, 12:43:20 GMT–Neural Information Processing Systems 

Both NS and QD are explained in detail in Sec. 3. ES directly searches in the parameter space of a neural network to find an effective policy.