Zobrazeno 1 - 10
of 551
pro vyhledávání: '"Ronen, I."'
Autor:
Goldsztejn, Elias, Brafman, Ronen I.
Classical navigation planners can provide safe navigation, albeit often suboptimally and with hindered human norm compliance. ML-based, contemporary autonomous navigation algorithms can imitate more natural and humancompliant navigation, but usually
Externí odkaz:
http://arxiv.org/abs/2403.18524
Publikováno v:
EPTCS 362, 2022, pp. 98-111
To enable robots to achieve high level objectives, engineers typically write scripts that apply existing specialized skills, such as navigation, object detection and manipulation to achieve these goals. Writing good scripts is challenging since they
Externí odkaz:
http://arxiv.org/abs/2207.09713
Publikováno v:
In Artificial Intelligence June 2024 331
Autor:
Abadi, Eden, Brafman, Ronen I.
Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular
Externí odkaz:
http://arxiv.org/abs/2003.01008
Autor:
Gaon, Maor, Brafman, Ronen I.
The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing coffee on
Externí odkaz:
http://arxiv.org/abs/1912.02552
Autor:
Beimel, Amos, Brafman, Ronen I.
In privacy-preserving multi-agent planning, a group of agents attempt to cooperatively solve a multi-agent planning problem while maintaining private their data and actions. Although much work was carried out in this area in past years, its theoretic
Externí odkaz:
http://arxiv.org/abs/1810.13354
We describe a novel approach to monitoring high level behaviors using concepts from AI planning. Our goal is to understand what a program is doing based on its system call trace. This ability is particularly important for detecting malware. We approa
Externí odkaz:
http://arxiv.org/abs/1709.03363
Autor:
Shekhar, Shashank, Brafman, Ronen I.
Publikováno v:
In Artificial Intelligence January 2020 278
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Brafman, Ronen I., Shani, Guy
Publikováno v:
Journal Of Artificial Intelligence Research, Volume 45, pages 565-600, 2012
Replanning via determinization is a recent, popular approach for online planning in MDPs. In this paper we adapt this idea to classical, non-stochastic domains with partial information and sensing actions, presenting a new planner: SDR (Sample, Deter
Externí odkaz:
http://arxiv.org/abs/1401.6048