Post by Roberta Raileanu: Great work on improving sample efficiency in RL via resets, which allows more updates and thus better...

Post

Roberta Raileanu @robertarail · Feb 8, 2023

From Twitter

Great work on improving sample efficiency in RL via resets, which allows more updates and thus better scaling with compute. Love the simplicity of the method and the many insights in the paper.

Tweet Feb 3, 2023

Our paper "Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier" has been accepted to ICLR as top 5%! We show that lots of updates and resets lead to great sample efficiency. Come for the scaling, stay for the insights. o

by Pierluca D'Oro

Recommended by 1 person

1 mention

Replies

No replies yet