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

NeurIPS 2018 Edoardo ContiVashisht MadhavanFelipe Petroski SuchJoel LehmanKenneth O. StanleyJeff Clune

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 challenging deep reinforcement learning (RL) problems, but are much faster (e.g. hours vs. days) because they parallelize better. However, many RL problems require directed exploration because they have reward functions that are sparse or deceptive (i.e. contain local optima), and it is unknown how to encourage such exploration with ES... (read more)

PDF Abstract

Evaluation results from the paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.