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.
At very long memory (α= 0.9), the system settles close to the ergodic phase, withϵvalues slightly larger than 0
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
nlin.AO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.