Abstract | ||
---|---|---|
Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs. Their attraction is due in part to the fact that they can represent a general class of methods that allow to learn a solution with a reasonably set reward and minimal prior knowledge, even in situations where it is difficult or expensive for a human expert. For RL to truly make good on this promise, however, we need algorithms and learning setups that can work across a broad range of problems with minimal problem specific adjustments or engineering. In this paper, we study this idea of generality in the locomotion domain. We develop a learning framework that can learn sophisticated locomotion behavior for a wide spectrum of legged robots, such as bipeds, tripeds, quadrupeds and hexapods, including wheeled variants. Our learning framework relies on a data-efficient, off-policy multi-task RL algorithm and a small set of reward functions that are semantically identical across robots. To underline the general applicability of the method, we keep the hyper-parameter settings and reward definitions constant across experiments and rely exclusively on on-board sensing. For nine different types of robots, including a real-world quadruped robot, we demonstrate that the same algorithm can rapidly learn diverse and reusable locomotion skills without any platform specific adjustments or additional instrumentation of the learning setup. |
Year | Venue | DocType |
---|---|---|
2020 | CoRL | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roland Hafner | 1 | 15 | 2.49 |
Tim Hertweck | 2 | 0 | 1.35 |
Philipp Klöppner | 3 | 0 | 0.34 |
Michael Blösch | 4 | 427 | 31.24 |
M. Neunert | 5 | 65 | 9.95 |
markus wulfmeier | 6 | 51 | 6.86 |
Saran Tunyasuvunakool | 7 | 10 | 2.14 |
Nicolas Heess | 8 | 1762 | 94.77 |
Martin Riedmiller | 9 | 5655 | 366.29 |