evolution strategy
CMA-ES with Optimal Covariance Update and Storage Complexity
Oswin Krause, Dídac Rodríguez Arbonès, Christian Igel
Neural Information Processing Systems http://nips.cc/
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep reinforcement learning (RL) problems, but are much faster (e.g.
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies Oscar Li1, James Harrison, Jascha Sohl-Dickstein, Virginia Smith
First-order optimization methods are a foundational tool in machine learning.
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies Oscar Li1, James Harrison, Jascha Sohl-Dickstein, Virginia Smith
First-order optimization methods are a foundational tool in machine learning.
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth Stanley, Jeff Clune
Neural Information Processing Systems http://nips.cc/
Simple random search of static linear policies is competitive for reinforcement learning
Horia Mania, Aurelia Guy, Benjamin Recht
Model-free reinforcement learning aims to offer off-the-shelf solutions for controlling dynamical systems without requiring models of the system dynamics.
NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications Robert Tjarko Lange
Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g.
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization
Krzysztof M. Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Vikas Sindhwani
Neural Information Processing Systems http://nips.cc/
Evolving Connectivity for Recurrent Spiking Neural Networks Guan Wang 1, 2, Y uhao Sun
Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics.