Zobrazeno 1 - 10
of 5 293
pro vyhledávání: '"Zisman A"'
In-context learning allows models like transformers to adapt to new tasks from a few examples without updating their weights, a desirable trait for reinforcement learning (RL). However, existing in-context RL methods, such as Algorithm Distillation (
Externí odkaz:
http://arxiv.org/abs/2411.01958
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 14, Pp 1215-1222 (2021)
Stephan Kress,1 Anja Borck,2 Ariel Zisman,3 Peter Bramlage,4,5 Thorsten Siegmund6 1Diabeteszentrum, Vinzentius-Krankenhaus, Landau, Germany; 2Medical Department, Sanofi, Berlin, Germany; 3The Endocrine Center of Aventura, Aventura, FL, USA; 4Institut
Externí odkaz:
https://doaj.org/article/2d50b4fbf1df49c791b196b15b67cc6f
Autor:
Nikulin, Alexander, Zisman, Ilya, Zemtsov, Alexey, Sinii, Viacheslav, Kurenkov, Vladislav, Kolesnikov, Sergey
Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back
Externí odkaz:
http://arxiv.org/abs/2406.08973
Autor:
Tripp, Charles Edison, Perr-Sauer, Jordan, Gafur, Jamil, Nag, Amabarish, Purkayastha, Avi, Zisman, Sagi, Bensen, Erik A.
Addressing the so-called ``Red-AI'' trend of rising energy consumption by large-scale neural networks, this study investigates the actual energy consumption, as measured by node-level watt-meters, of training various fully connected neural network ar
Externí odkaz:
http://arxiv.org/abs/2403.08151
Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously proposed models is their reliance on a predefined
Externí odkaz:
http://arxiv.org/abs/2312.13327
Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for data, which n
Externí odkaz:
http://arxiv.org/abs/2312.12275
Autor:
Nikulin, Alexander, Kurenkov, Vladislav, Zisman, Ilya, Agarkov, Artem, Sinii, Viacheslav, Kolesnikov, Sergey
Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX, XLand-MiniGrid is designed t
Externí odkaz:
http://arxiv.org/abs/2312.12044
Autor:
Zisman Alexander
Publikováno v:
Journal of the Mechanical Behavior of Materials, Vol 25, Iss 1-2, Pp 15-22 (2016)
Starting from Nye’s tensor, alternative characteristics of crystal curvature indicative of dislocation content are considered subject to very low thickness of investigated matter under the free surface and discreteness of orientation sampling. Anal
Externí odkaz:
https://doaj.org/article/64e698d119ce444ebef4a47936612360
Publikováno v:
AAMAS '23, Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (May 2023) Pages 49-57
The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private infor
Externí odkaz:
http://arxiv.org/abs/2306.08419
Autor:
Lior Zisman Zalis, Diego Posada
Publikováno v:
Re-visiones, Iss 9 (2024)
Externí odkaz:
https://doaj.org/article/ced1624e925240abbe6f7bb58140e168