Zobrazeno 1 - 10
of 353
pro vyhledávání: '"Tom Silver"'
A longstanding objective in classical planning is to synthesize policies that generalize across multiple problems from the same domain. In this work, we study generalized policy search-based methods with a focus on the score function used to guide th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::020ab1402178793376ff324c44e59188
http://arxiv.org/abs/2204.10420
http://arxiv.org/abs/2204.10420
Publikováno v:
PLoS Neglected Tropical Diseases, Vol 10, Iss 3, p e0004549 (2016)
BACKGROUND:Assessment of the response to the 2014-15 Ebola outbreak indicates the need for innovations in data collection, sharing, and use to improve case detection and treatment. Here we introduce a Machine Learning pipeline for Ebola Virus Disease
Externí odkaz:
https://doaj.org/article/4c0a41f4e8194662a9e0aa83507c7dfc
Autor:
Clement Gehring, Masataro Asai, Rohan Chitnis, Tom Silver, Leslie Kaelbling, Shirin Sohrabi, Michael Katz
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3aced596ec4f20d1269d75701dea6145
http://arxiv.org/abs/2109.14830
http://arxiv.org/abs/2109.14830
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Robotic planning problems in hybrid state and action spaces can be solved by integrated task and motion planners (TAMP) that handle the complex interaction between motion-level decisions and task-level plan feasibility. TAMP approaches rely on domain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8df53decfcb982a0a3b1c69410d8b76
https://doi.org/10.1109/iros51168.2021.9635941
https://doi.org/10.1109/iros51168.2021.9635941
In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e9f3923e843db79707554684fbb0181
http://arxiv.org/abs/2105.14074
http://arxiv.org/abs/2105.14074
Publikováno v:
IROS
How can we learn representations for planning that are both efficient and flexible? Task and motion planning models are a good candidate, having been very successful in long-horizon planning tasks—however, they’ve proved challenging for learning,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3f936df0876283b320abe551a90552d
https://doi.org/10.1109/iros45743.2020.9341535
https://doi.org/10.1109/iros45743.2020.9341535
Publikováno v:
Web of Science
Meta-planning, or learning to guide planning from experience, is a promising approach to improving the computational cost of planning. A general meta-planning strategy is to learn to impose constraints on the states considered and actions taken by th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::979ebeb9c59a8f5b09f9a76351a5aa59
Autor:
Rachel Holladay, Beomjoon Kim, Caelan Reed Garrett, Leslie Pack Kaelbling, Tomás Lozano-Pérez, Rohan Chitnis, Tom Silver
The problem of planning for a robot that operates in environments containing a large number of objects, taking actions to move itself through the world as well as to change the state of the objects, is known as task and motion planning (TAMP). TAMP p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::09b53ee732edec44681e3807d1e60114
Publikováno v:
AAAI
Humans can learn many novel tasks from a very small number (1--5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We propose an expressive class of policies, a strong but general prior, and a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::275f7cad552bdaf79972f9e1dbbf8cce
http://arxiv.org/abs/1904.06317
http://arxiv.org/abs/1904.06317