mlsanityData to 14 Oct 2026

Learning Robust Controllers Via Probabilistic Model-Based Policy Search

arXiv 2110.13576 ↗First posted 26 Oct 2021cs.LGcited by 1

On the map: World models → Latent dynamics models and model-based RL

Abstract (arXiv)

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts. We investigate whether controllers learned in such a way are robust and able to generalize under small perturbations of the environment. Our work is inspired by the PILCO algorithm, a method for probabilistic policy search. We show that enforcing a lower bound to the likelihood noise in the Gaussian Process dynamics model regularizes the policy updates and yields more robust controllers. We demonstrate the empirical benefits of our method in a simulation benchmark.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Latent dynamics models and model-based RL, one of 11 directions in World models. Builds on 16 of its 32 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

16 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2019When to Trust Your Model: Model-Based Policy Optimization19 Jun

Other references · 15

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  3. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 609
  4. 2017Robust Adversarial Reinforcement Learningcited by 451
  5. 2019Challenges of Real-World Reinforcement Learningcited by 291
  6. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  7. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 141
  8. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  9. 2019Robust Reinforcement Learning for Continuous Control with Model Misspecificationcited by 78
  10. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  11. 2019PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaoscited by 56
  12. 2018Meta Reinforcement Learning with Latent Variable Gaussian Processescited by 44
3 more
  1. 2020SAMBA: Safe Model-Based & Active Reinforcement Learningcited by 30
  2. 2018Learning Robust Optionscited by 17
  3. 2017Safe Policy Search with Gaussian Process Modelscited by 9

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Improving Controller Generalization with Dimensionless Markov Decision Processescited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search
  2. 2024UDUC: An Uncertainty-driven Approach for Learning-based Robust Control
  3. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
  4. 2021Safe Continuous Control with Constrained Model-Based Policy Optimization
  5. 2024Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces
  6. 2026Model-Based Reinforcement Learning for Control under Time-Varying Dynamics
  7. 2026All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
  8. 2024Robust Model Based Reinforcement Learning Using L1 Adaptive Control