Curious iLQR: Resolving Uncertainty in Model-based RL
This work addresses the challenge of efficient and reliable control learning in robotics, though it is incremental as it builds on existing model-based methods with a curiosity-driven twist.
The paper tackled the problem of improving model-based reinforcement learning for robotic manipulation by incorporating curiosity to reduce model uncertainty, resulting in more reliable target reaching and better generalization with fewer system rollouts.
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.