V-MIN: efficient reinforcement learning through demonstrations and relaxed reward demands
Visualitza/Obre
1608-V-MIN_-Efficient-Reinforcement-Learning-through-Demonstrations-and-Relaxed-Reward-Demands.pdf (376,4Kb) (Accés restringit)
Sol·licita una còpia a l'autor
Què és aquest botó?
Aquest botó permet demanar una còpia d'un document restringit a l'autor. Es mostra quan:
- Disposem del correu electrònic de l'autor
- El document té una mida inferior a 20 Mb
- Es tracta d'un document d'accés restringit per decisió de l'autor o d'un document d'accés restringit per política de l'editorial
Tipus de documentText en actes de congrés
Data publicació2015
Condicions d'accésAccés restringit per política de l'editorial
Abstract
Reinforcement learning (RL) is a common paradigm for learning tasks in robotics. However, a lot of exploration is usually required, making RL too slow for high-level tasks. We present V-MIN, an algorithm that integrates teacher demonstrations with RL to learn complex tasks faster. The algorithm combines active demonstration requests and autonomous exploration to find policies yielding rewards higher than a given threshold Vmin.
This threshold sets the degree of quality with which the robot is expected to complete the task, thus allowing the user to either opt for very good policies that require many learning experiences, or to be more permissive with sub-optimal policies that are easier to learn. The threshold can also be increased online to force the system to improve its policies until the desired behavior is obtained. Furthermore, the algorithm generalizes previously learned knowledge, adapting well to changes. The performance of V-MIN has been validated through experimentation, including domains from the international planning competition. Our approach achieves the desired behavior where previous algorithms failed.
CitacióMartínez, D., Alenyà, G., Torras, C. V-MIN: efficient reinforcement learning through demonstrations and relaxed reward demands. A: AAAI Conference on Artificial Intelligence. "Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence". Austin: 2015, p. 2857-2863.
Versió de l'editorhttp://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9634/9952
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
1608-V-MIN_-Eff ... Relaxed-Reward-Demands.pdf![]() | 376,4Kb | Accés restringit |
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya