Darwin's agential materials: evolutionary implications of multiscale competency in developmental biology

M Levin - Cellular and Molecular Life Sciences, 2023‏ - Springer
A critical aspect of evolution is the layer of developmental physiology that operates between
the genotype and the anatomical phenotype. While much work has addressed the evolution …

Neuroevolution: from architectures to learning

D Floreano, P Dürr, C Mattiussi - Evolutionary intelligence, 2008‏ - Springer
Artificial neural networks (ANNs) are applied to many real-world problems, ranging from
pattern classification to robot control. In order to design a neural network for a particular task …

[ספר][B] The alignment problem: How can machines learn human values?

B Christian - 2021‏ - books.google.com
'Vital reading. This is the book on artificial intelligence we need right now.'Mike Krieger,
cofounder of Instagram Artificial intelligence is rapidly dominating every aspect of our …

Embodied intelligence via learning and evolution

A Gupta, S Savarese, S Ganguli, L Fei-Fei - Nature communications, 2021‏ - nature.com
The intertwined processes of learning and evolution in complex environmental niches have
resulted in a remarkable diversity of morphological forms. Moreover, many aspects of animal …

Human-level performance in 3D multiplayer games with population-based reinforcement learning

M Jaderberg, WM Czarnecki, I Dunning, L Marris… - Science, 2019‏ - science.org
Reinforcement learning (RL) has shown great success in increasingly complex single-agent
environments and two-player turn-based games. However, the real world contains multiple …

Weight agnostic neural networks

A Gaier, D Ha - Advances in neural information processing …, 2019‏ - proceedings.neurips.cc
Not all neural network architectures are created equal, some perform much better than
others for certain tasks. But how important are the weight parameters of a neural network …

Alphastar: An evolutionary computation perspective

K Arulkumaran, A Cully, J Togelius - Proceedings of the genetic and …, 2019‏ - dl.acm.org
In January 2019, DeepMind revealed AlphaStar to the world---the first artificial intelligence
(AI) system to beat a professional player at the game of StarCraft II---representing a …

On the expressivity of markov reward

D Abel, W Dabney, A Harutyunyan… - Advances in …, 2021‏ - proceedings.neurips.cc
Reward is the driving force for reinforcement-learning agents. This paper is dedicated to
understanding the expressivity of reward as a way to capture tasks that we would want an …

Evolution-guided policy gradient in reinforcement learning

S Khadka, K Tumer - Advances in Neural Information …, 2018‏ - proceedings.neurips.cc
Abstract Deep Reinforcement Learning (DRL) algorithms have been successfully applied to
a range of challenging control tasks. However, these methods typically suffer from three core …

Evolved policy gradients

R Houthooft, Y Chen, P Isola, B Stadie… - Advances in …, 2018‏ - proceedings.neurips.cc
We propose a metalearning approach for learning gradient-based reinforcement learning
(RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent …