PufferLib 5.0 reportedly doubles state-of-the-art Craftax performance
The claim concerns reinforcement learning: a user reports “Double SOTA perf” on Craftax with PufferLib 5.0.
TLDR
A user credits PufferLib 5.0 with twice the state-of-the-art performance for reinforcement learning on Craftax, describing the result as “Double SOTA perf.”
Combined views
7K
1 Source, first seen 16d ago
97 likes