ray
ray copied to clipboard
Published
20 hours ago •
ray-project
ray-project
[RLlib] Deflake replay buffer demo - Up test size to leave a little more time for ReplayBufferDemo
Signed-off-by: Artur Niederfahrenhorst [email protected]
Why are these changes needed?
The replay buffer demo likes to take approx 10 iterations to reach the nice reward of 50 but often gets cancelled earlier (for example after 7 like in the picture) because it is marked as a test of size medium.
