mlsanityData to 14 Oct 2026

UDUC: An Uncertainty-driven Approach for Learning-based Robust Control

arXiv 2405.02598 ↗First posted 4 May 2024cs.LGcited by 0

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

Abstract (arXiv)

Learning-based techniques have become popular in both model predictive control (MPC) and reinforcement learning (RL). Probabilistic ensemble (PE) models offer a promising approach for modelling system dynamics, showcasing the ability to capture uncertainty and scalability in high-dimensional control scenarios. However, PE models are susceptible to mode collapse, resulting in non-robust control when faced with environments slightly different from the training set. In this paper, we introduce the uncertainty-driven robust control (UDUC) loss as an alternative objective for training PE models, drawing inspiration from contrastive learning. We analyze the robustness of UDUC loss through the lens of robust optimization and evaluate its performance on the challenging Real-world Reinforcement Learning (RWRL) benchmark, which involves significant environmental mismatches between the training and testing environments.

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 20 of its 38 references that are in the map. First posted on arXiv 4 May 2024.

Builds on

20 of 38 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  6. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  7. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  8. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  9. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  10. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  11. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
  12. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
8 more
  1. 2019Benchmarking Model-Based Reinforcement Learningcited by 162
  2. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 77
  3. 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69
  4. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  5. 2019Ensembles of Locally Independent Prediction Modelscited by 22
  6. 2023Understanding Contrastive Learning via Distributionally Robust Optimizationcited by 21
  7. 2022Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularizationcited by 7
  8. 2021Greedy Bayesian Posterior Approximation with Deep Ensemblescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Hybrid Cross-domain Robust Reinforcement Learning
  2. 2021Learning Robust Controllers Via Probabilistic Model-Based Policy Search
  3. 2024Time-Constrained Robust MDPs
  4. 2024RRLS : Robust Reinforcement Learning Suite
  5. 2020Overcoming Model Bias for Robust Offline Deep Reinforcement Learning
  6. 2026A Control Barrier Function-Constrained Model Predictive Control Framework for Safe Reinforcement Learning
  7. 2026Epistemic Robust Offline Reinforcement Learning
  8. 2024Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model