paper-with-me

홈 › Papers

Selection for short-term empowerment accelerates the evolution of homeostatic neural cellular automata

2023-05-24 · Caitlin Grasso, Josh Bongard

Empowerment -- a domain independent, information-theoretic metric -- has previously been shown to assist in the evolutionary search for neural cellular automata (NCA) capable of homeostasis when employed as a fitness function. In our previous study, we successfully extended empowerment, defined as maximum time-lagged mutual information between agents' actions and future sensations, to a distributed sensorimotor system embodied as an NCA. However, the time-delay between actions and their corresponding sensations was arbitrarily chosen. Here, we expand upon previous work by exploring how the time scale at which empowerment operates impacts its efficacy as an auxiliary objective to accelerate the discovery of homeostatic NCAs. We show that shorter time delays result in marked improvements over empowerment with longer delays, when compared to evolutionary selection only for homeostasis. Moreover, we evaluate stability and adaptability of evolved NCAs, both hallmarks of living systems that are of interest to replicate in artificial ones. We find that short-term empowered NCA are more stable and are capable of generalizing better to unseen homeostatic challenges. Taken together, these findings motivate the use of empowerment during the evolution of other artifacts, and suggest how it should be incorporated to accelerate evolution of desired behaviors for them. Source code for the experiments in this paper can be found at: https://github.com/caitlingrasso/empowered-nca-II.

📄 PDF Abstract BibTeX arXiv:2305.15220

Code (1)

caitlingrasso/empowered-nca-ii 공식 구현

Similar Papers 제목 키워드 기반

Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment

2026-06-05 · Subramanyam Sahoo arxiv

Culture is the most insidious vector of gradual human disempowerment by AI: unlike economic or political displacement, cultural displacement attacks the very preferences and values through which humans recognise and resi…

Information-Theoretic Policy Pre-Training with Empowerment

2025-10-07 · Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri 외 arxiv

Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for reinforcement learning (RL). Besides for un…

Reinforcement Learning

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage

2026-01-27 · Mrinank Sharma, Miles McCain, Raymond Douglas, David Duvenaud arxiv

Although AI assistants are now deeply embedded in society, there has been limited empirical study of how their usage affects human empowerment. We present the first large-scale empirical analysis of disempowerment patter…

Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning

2023-07-06 · Andrew Levy, Sreehari Rammohan, Alessandro Allievi, Scott Niekum 외

General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large collections of distinct skills, but mutual…

Hierarchical Reinforcement Learning

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

2023-10-30 · Seongun Kim, Kyowoon Lee, Jaesik Choi

Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximizat…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Navigation