Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fall with Grace

June 18, 2018 Β· Declared Dead Β· πŸ› Simulation, Modeling, and Programming for Autonomous Robots

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Steve Heim, Alexander SprΓΆwitz arXiv ID 1806.06569 Category cs.AI: Artificial Intelligence Cross-listed cs.RO Citations 1 Venue Simulation, Modeling, and Programming for Autonomous Robots Last Checked 4 months ago
Abstract
Despite impressive results using reinforcement learning to solve complex problems from scratch, in robotics this has still been largely limited to model-based learning with very informative reward functions. One of the major challenges is that the reward landscape often has large patches with no gradient, making it difficult to sample gradients effectively. We show here that the robot state-initialization can have a more important effect on the reward landscape than is generally expected. In particular, we show the counter-intuitive benefit of including initializations that are unviable, in other words initializing in states that are doomed to fail.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted