Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Sohrabi, Shirin"'
Planning remains one of the last standing bastions for large language models (LLMs), which now turn their attention to search. Most of the literature uses the language models as world models to define the search space, forgoing soundness for the sake
Externí odkaz:
http://arxiv.org/abs/2408.11326
Among the most important properties of algorithms investigated in computer science are soundness, completeness, and complexity. These properties, however, are rarely analyzed for the vast collection of recently proposed methods for planning with larg
Externí odkaz:
http://arxiv.org/abs/2404.11833
Developing domain models is one of the few remaining places that require manual human labor in AI planning. Thus, in order to make planning more accessible, it is desirable to automate the process of domain model generation. To this end, we investiga
Externí odkaz:
http://arxiv.org/abs/2405.06650
The ability to generate multiple plans is central to using planning in real-life applications. Top-quality planners generate sets of such top-cost plans, allowing flexibility in determining equivalent ones. In terms of the order between actions in a
Externí odkaz:
http://arxiv.org/abs/2404.01503
The growing utilization of planning tools in practical scenarios has sparked an interest in generating multiple high-quality plans. Consequently, a range of computational problems under the general umbrella of top-quality planning were introduced ove
Externí odkaz:
http://arxiv.org/abs/2403.03176
Autor:
Lee, Junkyu, Katz, Michael, Agravante, Don Joven, Liu, Miao, Tasse, Geraud Nangue, Klinger, Tim, Sohrabi, Shirin
Two common approaches to sequential decision-making are AI planning (AIP) and reinforcement learning (RL). Each has strengths and weaknesses. AIP is interpretable, easy to integrate with symbolic knowledge, and often efficient, but requires an up-fro
Externí odkaz:
http://arxiv.org/abs/2203.00669
Autor:
Gehring, Clement, Asai, Masataro, Chitnis, Rohan, Silver, Tom, Kaelbling, Leslie Pack, Sohrabi, Shirin, Katz, Michael
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems found in class
Externí odkaz:
http://arxiv.org/abs/2109.14830
In this paper, we address the knowledge engineering problems for hypothesis generation motivated by applications that require timely exploration of hypotheses under unreliable observations. We looked at two applications: malware detection and intensi
Externí odkaz:
http://arxiv.org/abs/1408.6520
Autor:
Sohrabi, Shirin, McIlraith, Sheila A.
In this paper, we address the problem of generating preferred plans by combining the procedural control knowledge specified by Hierarchical Task Networks (HTNs) with rich qualitative user preferences. The outcome of our work is a language for specify
Externí odkaz:
http://arxiv.org/abs/0909.0682
Autor:
Sohrabi, Shirin1 (AUTHOR) michael.katz1@ibm.com, Katz, Michael1 (AUTHOR) michael.katz1@ibm.com, Hassanzadeh, Oktie1 (AUTHOR), Udrea, Octavian1 (AUTHOR), Feblowitz, Mark D.1 (AUTHOR), Riabov, Anton2 (AUTHOR), Weng, Paul (AUTHOR)
Publikováno v:
AI Communications. 2019, Vol. 32 Issue 1, p1-13. 13p.