Abstract | ||
---|---|---|
We introduce MixM using our method to progress through an action-space curriculum we achieve both faster training and better final performance than one obtains using traditional methods. (2) We further show that Mu0026M can be used successfully to progress through a curriculum of architectural variants defining an agents internal state. (3) Finally, we illustrate how a variant of our method can be used to improve agent performance in a multitask setting. |
Year | Venue | DocType |
---|---|---|
2018 | international conference on machine learning | Journal |
Volume | Citations | PageRank |
abs/1806.01780 | 2 | 0.35 |
References | Authors | |
13 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wojciech Marian Czarnecki | 1 | 338 | 23.53 |
Siddhant M. Jayakumar | 2 | 11 | 5.55 |
Max Jaderberg | 3 | 1614 | 54.60 |
Leonard Hasenclever | 4 | 20 | 5.42 |
Yee Whye Teh | 5 | 6253 | 539.26 |
Nicolas Heess | 6 | 1762 | 94.77 |
Simon Osindero | 7 | 4878 | 398.74 |
Razvan Pascanu | 8 | 2596 | 199.21 |