mlsanityData to 7 Oct 2026

Sample-efficient Cross-Entropy Method for Real-time Planning

arXiv 2008.06389 ↗First posted 14 Aug 2020cs.LG cs.RO stat.MLcited by 90

Not on the map. Why?

Abstract (arXiv)

Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents them from being used for real-time planning and control. We propose an improved version of the CEM algorithm for fast planning, with novel additions including temporally-correlated actions and memory, requiring 2.7-22x less samples and yielding a performance increase of 1.2-10x in high-dimensional control problems.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 17; 2023: 14; 2024: 14; 2025: 13; 2026: 28.

90 papers.

Sort:

By area:

  1. 2023Optimistic Active Exploration of Dynamical Systemscited by 32
  2. 2022Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulationcited by 29
  3. 2022DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systemscited by 27
  4. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  5. 2021Learning Dynamics Models for Model Predictive Agentscited by 21
  6. 2022Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performancecited by 21
  7. 2025Learning Getting-Up Policies for Real-World Humanoid Robotscited by 21
  8. 2026Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Modelscited by 21
  9. 2022Combining Evolution and Deep Reinforcement Learning for Policy Search: a Surveycited by 20
  10. 2021Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domainscited by 18
  11. 2022Style-ERD: Responsive and Coherent Online Motion Style Transfercited by 17
  12. 2023Distributionally Robust Model-based Reinforcement Learning with Large State Spacescited by 17
38 more
  1. 2021An Experimental Design Perspective on Model-Based Reinforcement Learningcited by 16
  2. 2022Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projectioncited by 13
  3. 2026Latent Geometry Beyond Search: Amortizing Planning in World Modelscited by 13
  4. 2026stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluationcited by 13
  5. 2022Learning to Get Upcited by 11
  6. 2022Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processescited by 10
  7. 2022Learning Sampling Distributions for Model Predictive Controlcited by 10
  8. 2022Exploration via Planning for Information about the Optimal Trajectorycited by 8
  9. 2022Hierarchical Policy Blending as Inference for Reactive Robot Controlcited by 8
  10. 2023Constrained Stein Variational Trajectory Optimizationcited by 8
  11. 2025Continual Reinforcement Learning by Planning with Online World Modelscited by 8
  12. 2025Test-time Offline Reinforcement Learning on Goal-related Experiencecited by 8
  13. 2024A Pontryagin Perspective on Reinforcement Learningcited by 7
  14. 2025SOMBRL: Scalable and Optimistic Model-Based RLcited by 7
  15. 2026Test-Time Trajectory Optimization for Autonomous Drivingcited by 7
  16. 2021CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learningcited by 6
  17. 2023Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learningcited by 6
  18. 2024Zero-shot Model-based Reinforcement Learning using Large Language Modelscited by 6
  19. 2026Parallel Stochastic Gradient-Based Planning for World Modelscited by 6
  20. 2022A Simple Decentralized Cross-Entropy Methodcited by 5
  21. 2023Regularity as Intrinsic Reward for Free Playcited by 5
  22. 2025Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Controlcited by 5
  23. 2025Why and How Auxiliary Tasks Improve JEPA Representationscited by 5
  24. 2026Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Controlcited by 5
  25. 2022Continuous Monte Carlo Graph Searchcited by 4
  26. 2023PcLast: Discovering Plannable Continuous Latent Statescited by 4
  27. 2026Laplacian Representations for Decision-Time Planningcited by 4
  28. 2023Goal-conditioned Offline Planning from Curious Explorationcited by 3
  29. 2024D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulationcited by 3
  30. 2024NeoRL: Efficient Exploration for Nonepisodic RLcited by 3
  31. 2024Zero-Shot Offline Imitation Learning via Optimal Transportcited by 3
  32. 2025Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimizationcited by 3
  33. 2025Sample-efficient and Scalable Exploration in Continuous-Time RLcited by 3
  34. 2026IMWM: Intuition Models Complement World Models for Latent Planningcited by 3
  35. 2026LeFlow: Generative Latent Flow Planning for World Modelscited by 3
  36. 2022Inference of Affordances and Active Motor Control in Simulated Agentscited by 2
  37. 2022Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equationscited by 2
  38. 2023Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learningcited by 2

50 most cited of 90 All 90 (JSON)