Tangled Nature: A model of emergent structure and temporal mode among co-evolving agents
Understanding systems level behaviour of many interacting agents is challenging in various ways, here we'll focus on the how the interaction between components can lead to hierarchical structures with different types of dynamics, or causations, at different levels. We use the Tangled Nature model to discuss the co-evolutionary aspects connecting the microscopic level of the individual to the macroscopic systems level. At the microscopic level the individual agent may undergo evolutionary changes due to mutations of strategies. The micro-dynamics always run at a constant rate. Nevertheless, the system's level dynamics exhibit a completely different type of intermittent abrupt dynamics where major upheavals keep throwing the system between meta-stable configurations. These dramatic transitions are described by a log-Poisson time statistics. The long time effect is a collectively adapted of the ecological network. We discuss the ecological and macroevolutionary consequences of the adaptive dynamics and briefly describe work using the Tangled Nature framework to analyse problems in economics, sociology, innovation and sustainability
Code (0)
등록된 구현이 없습니다.
Tasks
SociologySimilar Papers 제목 키워드 기반
Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth
The navigation of complex labyrinths with tens of rooms under visual partially observable state is typically addressed using recurrent deep reinforcement learning architectures. In this work, we show that navigation can …
AttributeDeep Reinforcement LearningHigh-resolution Face Swapping via Latent Semantics Disentanglement
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their q…
DisentanglementFace SwappingHallucinationVocal Bursts Intensity PredictionTemporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training. This issue is especially problematic for image-based RL, where a…
Disentanglementreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1CCAR: Intrinsic Robustness as an Emergent Geometric Property
Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled and brittle. We propose Class-Conditiona…
Emergent Compositional Communication for Latent World Properties
Can multi-agent communication pressure extract discrete, compositional representations of invisible physical properties from frozen video features? We show that agents communicating through a Gumbel-Softmax bottleneck wi…