Go-Explore: a New Approach for Hard-Exploration Problems

30 Jan 2019Adrien Ecoffet • Joost Huizinga • Joel Lehman • Kenneth O. Stanley • Jeff Clune

On Montezuma's Revenge, Go-Explore scores a mean of over 43k points, almost 4 times the previous state of the art. Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge. On Pitfall, Go-Explore with domain knowledge is the first algorithm to score above zero.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.