Abstract | ||
---|---|---|
We train a neural network to control a drumstick fastened to a motor. The network takes a temporally arranged sequence of desired strikes, or a rhythm, as input and outputs a sequence of motor velocities controlling the drumstick's physical movement. We use a new method of training, we call Collaborative Network Training, in which three networks work together to directly minimize a non-differentiable loss function. In this work, the goal is to minimize the difference between the input sequence and the resulting drumstick strikes on a surface produced by the network outputs. The resulting policy learned by the network works in real-time and has a precision of 10 milliseconds. |
Year | DOI | Venue |
---|---|---|
2019 | 10.5555/3306127.3332105 | adaptive agents and multi-agents systems |
Keywords | Field | DocType |
Robot learning,robot controls | Robot learning,Computer science,Artificial intelligence,Collaborative network,Artificial neural network,Distributed computing | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mason Bretan | 1 | 18 | 2.28 |
Sanan Siddharth | 2 | 16 | 2.27 |
Larry P. Heck | 3 | 1096 | 100.58 |