# Curious iLQR: Resolving Uncertainty in Model-based RL

arXiv: https://arxiv.org/abs/1904.06786 · HTML: https://mlsanity.com/paper/1904.06786/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 11 of 11)

- [Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning](https://mlsanity.com/paper/2210.05927/) (2022)
- [Regularized Newton Method with Global O(1/k2) Convergence](https://mlsanity.com/paper/2112.02089/) (2021)
- [Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models](https://mlsanity.com/paper/2301.04741/) (2023)
- [Active Exploration for Robotic Manipulation](https://mlsanity.com/paper/2210.12806/) (2022)
- [Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics](https://mlsanity.com/paper/2305.12240/) (2023)
- [Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting](https://mlsanity.com/paper/2106.11712/) (2021)
- [First Order Model-Based RL through Decoupled Backpropagation](https://mlsanity.com/paper/2509.00215/) (2025)
- [Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models](https://mlsanity.com/paper/2102.02493/) (2021)
- [Learning Soft Robotic Dynamics with Active Exploration](https://mlsanity.com/paper/2510.27428/) (2025)
- [Model Based Meta Learning of Critics for Policy Gradients](https://mlsanity.com/paper/2204.02210/) (2022)
- [Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations](https://mlsanity.com/paper/2307.12062/) (2023)

## 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.