Curious iLQR: Resolving Uncertainty in Model-based RL
Not on the map. Why?
Abstract (arXiv)
Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based reinforcement learning (MBRL) framework that combines Bayesian modeling of the system dynamics with curious iLQR, an iterative LQR approach that considers model uncertainty. During trajectory optimization the curious iLQR attempts to minimize both the task-dependent cost and the uncertainty in the dynamics model. We demonstrate the approach on reaching tasks with 7-DoF manipulators in simulation and on a real robot. Our experiments show that MBRL with curious iLQR reaches desired end-effector targets more reliably and with less system rollouts when learning a new task from scratch, and that the learned model generalizes better to new reaching tasks.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Apr 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 3; 2023: 3; 2024: 0; 2025: 2.
11 papers.
- 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 43
- 2021Regularized Newton Method with Global O(1/k2) Convergencecited by 22
- 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Modelscited by 21
- 2022Active Exploration for Robotic Manipulationcited by 10
- 2023Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamicscited by 7
- 2021Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shootingcited by 6
- 2025First Order Model-Based RL through Decoupled Backpropagationcited by 5
- 2021Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Modelscited by 2
- 2025Learning Soft Robotic Dynamics with Active Explorationcited by 2
- 2022Model Based Meta Learning of Critics for Policy Gradientscited by 0
- 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
- 2025Learning Soft Robotic Dynamics with Active Exploration31 Oct 2025
- 2025First Order Model-Based RL through Decoupled Backpropagation29 Aug 2025
- 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations22 Jul 2023
- 2023Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics20 May 2023
- 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models11 Jan 2023
- 2022Active Exploration for Robotic Manipulation23 Oct 2022
- 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning12 Oct 2022
- 2022Model Based Meta Learning of Critics for Policy Gradients5 Apr 2022
- 2021Regularized Newton Method with Global O(1/k2) Convergence3 Dec 2021
- 2021Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting22 Jun 2021
- 2021Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models4 Feb 2021