The Cross-Entropy Method

By Reuven Y. Rubinstein, Dirk P. Kroese. 2004

Subfields: Probabilistic & Bayesian Methods, Mathematical Optimization

How researchers see this paper

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

In Probabilistic & Bayesian Methods

1. Sergey Levine
2. Chelsea Finn
3. Josh Tenenbaum
4. Michael Janner
5. Pieter Abbeel
6. Jan Peters
7. William T. Freeman
8. Jiajun Wu

In Mathematical Optimization

1. Peter Pastor
2. Mrinal Kalakrishnan
3. Stefan Schaal
4. Pieter Abbeel
5. Ludovic Righetti
6. T. T. Gomes
7. J. Bishop
8. Jan Peters

Citations in the corpus

• End-to-End Training of Deep Visuomotor Policies (2015, neutral): “, 2010), reward-weighted regression (RWR) (Peters and Schaal, 2007; Kober and Peters, 2009), the cross-entropy method (CEM) (Rubinstein and Kroese, 2004), and PILCO (Deisenroth and Rasmussen, 2011).”
• Reinforcement learning in robotics: A survey (2013, methodology): “…et al., 2006; Roberts et al., 2010), and general stochastic optimization methods (such as Nelder–Mead (Bagnell and Schneider, 2001), cross-entropy (Rubinstein and Kroese, 2004) and population-based methods (Goldberg, 1989)) to approaches coming from optimal control such as DDP (Atkeson,…”
• Reasoning About Physical Interactions with Object-Oriented Prediction and Planning (2018, methodology): “In practice, we used CEM starting from a uniform distribution with five iterations, 1000 samples per iteration, and used the top 10% of samples to fit the subsequent iteration’s sampling distribution.”
• Importance Nested Sampling and the MultiNest Algorithm (2013, methodology): “As suggested by their given numerical examples this approach appears superior to other adaptive importance sampling schemes (e.g. the cross-entropy method; cf. Rubinstein and Kroese 2004) in which the past draws from sub-optimal proposals are ultimately discarded.”
• Advanced global optimisation for mission analysis and design (2004, background): “Cross Entropy, originally developed for combinatorial optimisation [29], uses a Gaussian distribution to progressively bias the sampling of point towards a global optimum.”
• AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos (2019, methodology): “that we use is the latent space model-predictive control (MPC) method described in [49], which involves iteratively searching for an optimal sequence of actions using the cross-entropy method (CEM) [55], a sampling-based optimization procedure.”
• Automatically generating commit messages from diffs using neural machine translation (2017, unknown): “The training goal is cross-entropy minimization [49].”
• Neural Machine Translation with Supervised Attention (2016, background): “Since for each t, α(θ)t is a distribution, it is natural to use CE as the metric to evaluate the disagreement (Rubinstein and Kroese, 2004).”