Abstract | ||
---|---|---|
In this paper, We study the problem of learning a controllable representation for high-dimensional observations of dynamical systems. Specifically, we consider a situation where there are multiple sets of observations of dynamical systems with identical underlying dynamics. Only one of these sets has information about the effect of actions on the observation and the rest are just some random observations of the system. Our goal is to utilize the information in that one set and find a representation for the other sets that can be used for planning and ling-term prediction. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Learning | Theoretical computer science,Dynamical systems theory,Artificial intelligence,Mathematics,Machine learning |
DocType | Volume | Citations |
Journal | abs/1711.09165 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ershad Banijamali | 1 | 8 | 2.57 |
Ahmad Khajenezhad | 2 | 0 | 0.34 |
Ali Ghodsi | 3 | 3306 | 156.01 |
Mohammad Ghavamzadeh | 4 | 814 | 67.73 |