544 citations · 906 across the 5 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.NE2017★ 544 cited
Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti +3
Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algo…
cs.AI2017★ 114 cited
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such +3
Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challeng…