Scaling simulation-to-real transfer by learning composable robot skills
International Symposium on Experimental Robotics, Volume abs/1809.10253, 2018.
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and parameterization of low-le...More
Full Text (Upload PDF)
PPT (Upload PPT)