3 papers
cs.RO2022
Designing a Robust Low-Level Agnostic Controller for a Quadrotor with Actor-Critic Reinforcement Learning
Guilherme Siqueira Eduardo, Wouter Caarls
Purpose: Real-life applications using quadrotors introduce a number of disturbances and time-varying properties that pose a challenge to flight controllers. We observed that, when…
cs.LG2022
Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning
Renata Garcia, Wouter Caarls
Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. However, even state o…
cs.RO2021
Deep Reinforcement Learning with Embedded LQR Controllers
Wouter Caarls
Reinforcement learning is a model-free optimal control method that optimizes a control policy through direct interaction with the environment. For reaching tasks that end in regula…