mlsanityData to 14 Oct 2026

Bregman Centroid Guided Cross-Entropy Method

arXiv 2506.02205 ↗First posted 2 Jun 2025cs.LG cs.AI cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

The Cross-Entropy Method (CEM) is a widely adopted trajectory optimizer in model-based reinforcement learning (MBRL), but its unimodal sampling strategy often leads to premature convergence in multimodal landscapes. In this work, we propose Bregman Centroid Guided CEM (BC-EvoCEM), a lightweight enhancement to ensemble CEM that leverages textitBregman centroids for principled information aggregation and diversity control. textbfBC-EvoCEM computes a performance-weighted Bregman centroid across CEM workers and updates the least contributing ones by sampling within a trust region around the centroid. Leveraging the duality between Bregman divergences and exponential family distributions, we show that textbfBC-EvoCEM integrates seamlessly into standard CEM pipelines with negligible overhead. Empirical results on synthetic benchmarks, a cluttered navigation task, and full MBRL pipelines demonstrate that textbfBC-EvoCEM enhances both convergence and solution quality, providing a simple yet effective upgrade for CEM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 25 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

10 of 25 references.

References · 10

  1. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  2. 2018World Modelscited by 1,513
  3. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  4. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  5. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
  6. 2019Benchmarking Model-Based Reinforcement Learningcited by 162
  7. 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 95
  8. 2020Efficient constrained sampling via the mirror-Langevin algorithmcited by 55
  9. 2019Variational Inference MPC for Bayesian Model-based Reinforcement Learningcited by 39
  10. 2022A Simple Decentralized Cross-Entropy Methodcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization
  2. 2025Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition
  3. 2025CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
  4. 2026Cross-entropy optimization with prioritized constraints ↗
  5. 2026Bridging Dynamics Gaps via Diffusion Schr"odinger Bridge for Cross-Domain Reinforcement Learning
  6. 2025Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning
  7. 2026Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
  8. 2024CAGES: Cost-Aware Gradient Entropy Search for Efficient Local Multi-Fidelity Bayesian Optimization