Towards domain-independent biases for action selection in robotic task-planning under uncertainty
Autor(en): | Saborío, J.C. Hertzberg, J. |
Herausgeber: | Rocha, A.P. van den Herik, J. |
Stichwörter: | Action Selection; Clear specifications; Domain independents; High costs; Large domain; Monte-Carlo Planning; Planning under uncertainty; Planning under Uncertainty.; Robotic tasks; Robotics, Action selection; Task planning, Robot programming | Erscheinungsdatum: | 2018 | Herausgeber: | SciTePress | Journal: | ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence | Volumen: | 2 | Startseite: | 85 | Seitenende: | 93 | Zusammenfassung: | Task-planning algorithms for robots must quickly select actions with high reward prospects despite the huge variability of their domains, and accounting for the high cost of performing the wrong action in the “real-world”. In response we propose an action selection method based on reward-shaping, for planning in (PO)MDP's, that adds an informed action-selection bias but depends almost exclusively on a clear specification of the goal. Combined with a derived rollout policy for MCTS planners, we show promising results in relatively large domains of interest to robotics. Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved |
Beschreibung: | Conference of 10th International Conference on Agents and Artificial Intelligence, ICAART 2018 ; Conference Date: 16 January 2018 Through 18 January 2018; Conference Code:134807 |
ISBN: | 9789897582752 | DOI: | 10.5220/0006578500850093 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85046656759&doi=10.5220%2f0006578500850093&partnerID=40&md5=43f6820f5dd6f140ef02e2d3640d42c5 |
Zur Langanzeige
Seitenaufrufe
6
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 01.06.2024