Name
Abstract | ||
|---|---|---|
Can we learn a control policy able to adapt its behaviour in real time so as to take any desired amount of risk? The general Reinforcement Learning framework solely aims at optimising a total reward in expectation, which may not be desirable in critical applications. In stark contrast, the Budgeted Markov Decision Process (BMDP) framework is a formalism in which the notion of risk is implemented as a hard constraint on a failure signal. Existing algorithms solving BMDPs rely on strong assumptions and have so far only been applied to toy-examples. In this work, we relax some of these assumptions and demonstrate the scalability of our approach on two practical problems: a spoken dialogue system and an autonomous driving task. On both examples, we reach similar performances as Lagrangian Relaxation methods with a significant improvement in sample and memory efficiency. |
Year | Venue | DocType |
|---|---|---|
2019 | arXiv: Learning | Journal |
Volume | Citations | PageRank |
abs/1903.01004 | 0 | 0.34 |
References | Authors | |
10 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nicolas Carrara | 1 | 0 | 0.68 |
| Edouard Leurent | 2 | 0 | 0.34 |
| Romain Laroche | 3 | 110 | 17.35 |
| Tanguy Urvoy | 4 | 10 | 1.33 |
| Odalric-Ambrym Maillard | 5 | 171 | 26.40 |
| Olivier Pietquin | 6 | 664 | 68.60 |