Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning
Dec 21, 2020
|
IEEE Robotics and Automation Letters
We explored how MBRL can learn multi-step, nonlinear controllers!
Full PageModel Learning
←All ResearchStructured tools for predicting into the future
Modeling learning is the process of taking logged data and utilizing it to create a tool for predicting into the future. My work here started in the area of model-based reinforcement learning, but it is broad enough now that it warrants its own category. Model learning from batch data is also of great interest. If we can learn a useful model, we can leverage all the data we have logged to its fullest extent.
Open areas of study:
- Models for long-term predictions,
- Changing model training to prioritize task performance over accuracy,
- Model predictions with multi-modal data,
- Applications of low-data model learning.
Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning
Dec 16, 2020
|
Arxiv
Trying to reframe the MBRL framework with long-term predictions instead of one-step predictions!
Full Page
Objective Mismatch in Model-based Reinforcement Learning
Feb 11, 2020
|
2020 Conference on Learning for Decision and Control
Studying the numerical effects of a dual-optimization problem in model-based reinforcement learning -- control and dynamics. When optimizing model accuracy, there is no guarantee on improving task performance!
Full Page
Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning
Jan 11, 2019
|
IEEE Robotics and Automation Letters
We used deep model-based reinforcement learning to have a quadrotor learn to hover from less than 5 minutes of all experimental training data.
Full Page