arXiv cs.NE
· Papers
Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning
arXiv:2607.26059v1 Announce Type: cross Abstract: We report a striking phenomenon: deep reinforcement learning agents trained with frozen, randomly initialized CNN feature extractors spontaneously develop extremely sparse fully-connected representations, without any sparsity-inducing objective. In the first fully-conne