
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 PageRobotics is likely the biggest category of my work. It encompasses everything from hardware development to algorithmic studies all with the central goal of creating agents that can better interact with our physical world (even in indirect ways, like traffic lights).
I have so many open areas of research here, and am open to inquiries.