Pierre-Yves Oudeyer Profile picture
Research director @inria, Head of @flowersInria lab. Studying autonomous learning and curiosity in AI, machine learning, cognitive sciences, and education.
Jul 6, 2018 11 tweets 7 min read
How many random seeds are needed to compare #DeepRL algorithms?

Our new tutorial to address this key issue of #reproducibility in #reinforcementlearning

PDF: arxiv.org/pdf/1806.08295…

Code: github.com/flowersteam/rl…

Blog: openlab-flowers.inria.fr/t/how-many-ran…

#machinelearning #neuralnetworks Algo1 and Algo2 are two famous #DeepRL algorithms, here tested
on the Half-Cheetah #opengym benchmark.

Many papers in the litterature compare using 4-5 random seeds,
like on this graph which suggests that Algo1 is best.

Is this really the case?