google-research/rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

4 best points · 1 comments · 1 Hacker News post · 878 GitHub stars · View on GitHub

Hacker News discussions

• Deep Reinforcement Learning at the Edge of the Statistical Precipice (4 points, 1 comments, by my_hn, 2021-10-17)