TY - GEN
T1 - A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots
AU - Lynnerup, Nicolai Anton
AU - Nolling Jensen, Laura
AU - Hasle, Rasmus
AU - Hallam, John
PY - 2020
Y1 - 2020
N2 - As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are, however, notoriously hard to reproduce due to the algorithms’ intrinsic variance, the environments’ stochasticity, and numerous (potentially unreported) hyper-parameters. In this work we investigate the many issues leading to irreproducible research and how to manage those. We further show how to utilise a rigorous and standardised evaluation approach for easing the process of documentation, evaluation and fair comparison of different algorithms, where we emphasise the importance of choosing the right measurement metrics and conducting proper statistics on the results, for unbiased reporting of the results.
AB - As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are, however, notoriously hard to reproduce due to the algorithms’ intrinsic variance, the environments’ stochasticity, and numerous (potentially unreported) hyper-parameters. In this work we investigate the many issues leading to irreproducible research and how to manage those. We further show how to utilise a rigorous and standardised evaluation approach for easing the process of documentation, evaluation and fair comparison of different algorithms, where we emphasise the importance of choosing the right measurement metrics and conducting proper statistics on the results, for unbiased reporting of the results.
KW - CoRL
KW - robots
KW - learning
KW - reinforcement learning
KW - reproducibility
KW - statistics
M3 - Conference article
SN - 1532-4435
VL - 100
SP - 466
EP - 489
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
T2 - 3rd Conference on Robot Learning
Y2 - 30 October 2019 through 1 November 2019
ER -