EvoSK couples reinforcement learning with evolutionary replacement on a rugged landscape to self-organize at the edge of ergodicity breaking, yielding scale-free avalanches with exponent near -1.5 and superior rewards.
arXiv preprint arXiv:1909.05176 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
nlin.AO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Small LSTMs exhibit capacity-dependent near-critical branching as an emergent regime, with a mixture branching framework proposed to explain 1/f noise under subcritical conditions.
citing papers explorer
-
Self-Organization to the Edge of Ergodicity Breaking in a Complex Adaptive System
EvoSK couples reinforcement learning with evolutionary replacement on a rugged landscape to self-organize at the edge of ergodicity breaking, yielding scale-free avalanches with exponent near -1.5 and superior rewards.
-
Towards Critical Branching Mechanism in Recurrent Neural Networks
Small LSTMs exhibit capacity-dependent near-critical branching as an emergent regime, with a mixture branching framework proposed to explain 1/f noise under subcritical conditions.