Exponential natural evolution strategies

By Tobias Glasmachers, Tom Schaul, Yi Sun, Daan Wierstra, J. Urgen Schmidhuber. 2010

237 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Compact DCT-based descriptions can be evolved through NES or CoSyNE (Section 6.6).”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, methodology): “Therefore, we instead evolve the policy using a variant for Natural Evolution Strategies (NES; [25, 26]), called Separable NES (SNES; [19]).”
Evolution Strategies as a Scalable Alternative to Reinforcement Learning (2017, methodology): “The version of ES we use in this work belongs to the class of natural evolution strategies (NES) [Wierstra et al., 2008, 2014, Yi et al., 2009, Sun et al., 2009, Glasmachers et al., 2010a,b, Schaul et al., 2011] and is closely related to the work of Sehnke et al. [2010].”
Parameter Space Noise for Exploration (2017, background): “rge state spaces. Our work is also closely related to evolution strategies (ES, Rechenberg & Eigen (1973); Schwefel (1977)), and especially neural evolution strategies (NES, Sun et al. (2009a;b); Glasmachers et al. (2010a;b); Schaul et al. (2011); Wierstra et al. (2014)). In the context of polic”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1 RL through Direct and Indirect Search in RNN Program Space It is possible to train small RNNs with a few 100 or 1000 weights using evolutionary algorithms [200, 255, 105, 56, 68] to search the space of NN weights [165, 307, 44, 321, 180, 259, 320, 164, 173, 69, 71, 187, 121, 313, 66, 270, 269, 305”
One Big Net For Everything (2018, background): “Without a teacher, reward-maximizing programs of an RNN must be learned through repeated trial and error, e.g., through artiﬁcial evolution [39, 107, 83, 40, 16, 18, 103, 14, 89, 88] [76, Sec.”
Self-Delimiting Neural Networks (2012, background): “…through a focus on reducing search spaces by co-evolving the comparatively small weight vectors of individual neurons and synapses [19], by Natural Gradient-based Stochastic Search Strategies [80, 73, 74, 48, 17, 79], and by reducing search spaces through weight matrix compression [55, 35].”
Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport (2021, unknown): “…function is deﬁned as the following root mean square error (RMSE): where N str is the total number of structures in the training dataset, U tar ( n ) is the target energy of the n th structure, and U NEP ( n, z ) is the corresponding energy calculated using the NEP potential with the parameters z .”
Evolutionary algorithms and their applications to engineering problems (2020, unknown): “Exponential natural ES [62] Glasmachers et al.”
A linear time natural evolution strategy for non-separable functions (2011, unknown): “The state-of-the-art continuous black-box optimization algorithms, such as xNES [2] and CMA-ES [5], are all based on the same principle: a Gaussian search distribution is repeatedly adjusted according to the objective function evaluated at sampled points.”
Intrinsically motivated neuroevolution for vision-based reinforcement learning (2011, methodology): “The particular instantiation of UL-ERL in this paper uses a computationally efficient variant of Natural Evolution Strate gies (NES; [5,23,24,26]), called Separable NES or SNES [17] as the evolutionary search method, and a competitive clustering algorithm based on Vector Quantization (VQ; [7]) for ”
Reinforcement Learning Upside Down: Don't Predict Rewards - Just Map Them to Actions (2019, background): “RL is also very different from traditional black box optimization (BBO) [36, 57, 19, 9] such as neuroevolution [29, 59, 14, 12] which can be used to solve complex RL problems in partially observable environments [15] through iterative discovery of better and better parameters of an adaptive…”
Multifactorial Evolutionary Algorithm With Online Transfer Parameter Estimation: MFEA-II (2020, background): “These include the separable natural evolutionary strategy (SNES) [58] and the exponential natural evolutionary strategy (xNES) [59].”
The CMA Evolution Strategy: A Tutorial (2016, unknown): “The second line of (16) expresses the update in the natural coordinate system, an idea already considered in [12].”
Evolution Strategies (2018, methodology): “…the complete covariance matrix of the mutation distribution (compare Section 2.4) are correlated mutations [3], the generating set adaptation [26], the covariance matrix adaptation ( CMA ) [27], a muta-tive invariant adaptation [28], and some instances of natural evolution strategies [29, 30, 31].”