Chapter 3 – The Cross-Entropy Method for Optimization

By Zdravko I. Botev, Dirk P. Kroese, Reuven Y. Rubinstein, Pierre L'Ecuyer. 2013

273 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

Benchmarking Model-Based Reinforcement Learning (2019, methodology): “Shooting Algorithms: RS is very effective on simple tasks such as InvertedPendulum, CartPole and Acrobot, but as task difficulty increases RS gradually gets surpassed by PETS-RS and PETS-CEM, which indicates that modelling uncertainty aware dynamics is crucial for the performance of shooting algorit”
Deep Dynamics Models for Learning Dexterous Manipulation (2019, methodology): “Iterative Random-Shooting with Reﬁnement: To address these issues, much prior work [31] has instead taken a cross-entropy method (CEM) approach, which begins as the random shooting approach, but then does this sampling for multiple iterations m ∈ { 0 . . . used M } at each time step. update The top…”
Exploring Model-based Planning with Policy Networks (2019, methodology): “In PETS [5], the authors further use cross entropy method (CEM) [6, 1] to re-samples sequences near the best sequences from the last CEM iteration.”
Planning with Diffusion for Flexible Behavior Synthesis (2022, methodology): “Specifically, the role of learning is relegated to approximating environment dynamics; once learning is complete the model may be inserted into any of a variety of planning (Botev et al., 2013; Williams et al., 2015) or policy optimization (Sutton, 1990; Wang et al.”
Transfer Learning in Deep Reinforcement Learning: A Survey (2020, methodology): “Representative examples include the Monte-Carlo method dubbed random shooting [34] and its cross-entropy method (CEM) variants [35], [36].”
An Online Learning Approach to Model Predictive Control (2019, methodology): “A closely related approach is the cross-entropy method (CEM) [6], which also assumes a Gaussian sampling distribution but minimizes the KL divergence between the Gaussian distribution and a uniform distribution over low cost samples.”
A Survey of Multiobjective Evolutionary Algorithms Based on Decomposition (2017, unknown): “Based on the concept of the gD and an estimation of distribution algorithm (EDA), known as cross entropy (CE) [58], the authors proposed an algorithm termed as many-objective CE based on gD (MACE-gD).”