Showing cs.NEShow all
2 papers · 1 filter
cs.NE2024
Flow-Lenia.png: Evolving Multi-Scale Complexity by Means of Compression
Tadashi Adachi, Solvi Arnold, Takafumi Mochizuki +1
We propose a fitness measure quantifying multi-scale complexity for cellular automaton states, using compressibility as a proxy for complexity. The use of compressibility is ground…
cs.NE2024
Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets
Solvi Arnold, Reiji Suzuki, Takaya Arita +1
Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learn…