Zobrazeno 1 - 10
of 274
pro vyhledávání: '"Indelman, P."'
Autor:
Zhitnikov, Andrey, Indelman, Vadim
Taking into account future risk is essential for an autonomously operating robot to find online not only the best but also a safe action to execute. In this paper, we build upon the recently introduced formulation of probabilistic belief-dependent co
Externí odkaz:
http://arxiv.org/abs/2411.06711
Autor:
Kong, Da, Indelman, Vadim
Online planning under uncertainty in partially observable domains is an essential capability in robotics and AI. The partially observable Markov decision process (POMDP) is a mathematically principled framework for addressing decision-making problems
Externí odkaz:
http://arxiv.org/abs/2410.07630
Autor:
Pariente, Yaacov, Indelman, Vadim
Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem is modeled using partially observable Markov decision processes (POMDP
Externí odkaz:
http://arxiv.org/abs/2406.03000
Autor:
Indelman, Hedda Cohen, Hazan, Tamir
The Gumbel-Softmax probability distribution allows learning discrete tokens in generative learning, while the Gumbel-Argmax probability distribution is useful in learning discrete structures in discriminative learning. Despite the efforts invested in
Externí odkaz:
http://arxiv.org/abs/2406.02180
We introduce an innovative method for incremental nonparametric probabilistic inference in high-dimensional state spaces. Our approach leverages \slices from high-dimensional surfaces to efficiently approximate posterior distributions of any shape. U
Externí odkaz:
http://arxiv.org/abs/2405.16453
Autor:
Indelman, Hedda Cohen, Dahan, Elay, Perez-Agosto, Angeles M., Shiran, Carmit, Shaked, Doron, Daniel, Nati
Despite the remarkable success of deep learning in medical imaging analysis, medical image segmentation remains challenging due to the scarcity of high-quality labeled images for supervision. Further, the significant domain gap between natural and me
Externí odkaz:
http://arxiv.org/abs/2404.16325
Multi-robot belief space planning (MR-BSP) is essential for reliable and safe autonomy. While planning, each robot maintains a belief over the state of the environment and reasons how the belief would evolve in the future for different candidate acti
Externí odkaz:
http://arxiv.org/abs/2403.05962
Solving partially observable Markov decision processes (POMDPs) with high dimensional and continuous observations, such as camera images, is required for many real life robotics and planning problems. Recent researches suggested machine learned proba
Externí odkaz:
http://arxiv.org/abs/2311.07745
Continuous POMDPs with general belief-dependent rewards are notoriously difficult to solve online. In this paper, we present a complete provable theory of adaptive multilevel simplification for the setting of a given externally constructed belief tre
Externí odkaz:
http://arxiv.org/abs/2310.10274
Autor:
Barenboim, Moran, Indelman, Vadim
Autonomous agents operating in real-world scenarios frequently encounter uncertainty and make decisions based on incomplete information. Planning under uncertainty can be mathematically formalized using partially observable Markov decision processes
Externí odkaz:
http://arxiv.org/abs/2310.01791