Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Witwicki, Stefan J."'
Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA), from demonstrations. Unfortunately, these techni
Externí odkaz:
http://arxiv.org/abs/2402.07051
Autor:
Yildiz, Anil, Yel, Esen, Corso, Anthony L., Wray, Kyle H., Witwicki, Stefan J., Kochenderfer, Mykel J.
One of the bottlenecks of training autonomous vehicle (AV) agents is the variability of training environments. Since learning optimal policies for unseen environments is often very costly and requires substantial data collection, it becomes computati
Externí odkaz:
http://arxiv.org/abs/2305.18633
Autor:
Basich, Connor, Svegliato, Justin, Wray, Kyle Hollins, Witwicki, Stefan J., Zilberstein, Shlomo
Publikováno v:
EPTCS 319, 2020, pp. 37-53
Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios that an autonomous system may encounter. For an autonomous system to b
Externí odkaz:
http://arxiv.org/abs/2007.11740
Publikováno v:
PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS (AAMAS'15)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=core_ac_uk__::b364710a3229180d5494bf6761cddc8e
http://livrepository.liverpool.ac.uk/2032360/1/Oliehoek15AAMAS.pdf
http://livrepository.liverpool.ac.uk/2032360/1/Oliehoek15AAMAS.pdf
Publikováno v:
PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI)
Delft University of Technology
Delft University of Technology
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c35e79d17b832284846d7f5b06f6f87
Publikováno v:
MIT web domain
This paper presents a theoretical advance by which factored POSGs can be decomposed into local models. We formalize the interface between such local models as the influence agents can exert on one another; and we prove that this interface is sufficie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od________88::441257b4ff6b9648b4599281f94473e2
http://hdl.handle.net/1721.1/87052
http://hdl.handle.net/1721.1/87052
Publikováno v:
MIT web domain
Multiagent planning under uncertainty has seen important progress in recent years. Two techniques, in particular, have substantially advanced efficiency and scalability of planning. Multiagent heuristic search gains traction by pruning large portions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od________88::7df7b161bd6643572fc62b0ac51f68ed
http://hdl.handle.net/1721.1/100717
http://hdl.handle.net/1721.1/100717
Publikováno v:
Multi-Agent Systems (9783642347986); 2012, p189-204, 16p
Autor:
Witwicki, Stefan J., Durfee, Edmund H.
Publikováno v:
Service-oriented Computing: Agents, Semantics & Engineering (9783540799672); 2008, p134-148, 15p
Autor:
Witwicki, Stefan J., Durfee, Edmund H.
Publikováno v:
International Journal of Agent Oriented Software Engineering; January 2009, Vol. 3 Issue: 1 p59-87, 29p