Zobrazeno 1 - 10
of 279
pro vyhledávání: '"Lavaei, Javad"'
Autor:
Kim, Jihun, Lavaei, Javad
This paper is concerned with the online bandit nonlinear control, which aims to learn the best stabilizing controller from a pool of stabilizing and destabilizing controllers of unknown types for a given nonlinear dynamical system. We develop an algo
Externí odkaz:
http://arxiv.org/abs/2410.03230
Autor:
Kim, Jihun, Lavaei, Javad
This paper studies the linear system identification problem in the general case where the disturbance is sub-Gaussian, correlated, and possibly adversarial. First, we consider the case with noncentral (nonzero-mean) disturbances for which the ordinar
Externí odkaz:
http://arxiv.org/abs/2410.03218
Optimal control problems can be solved via a one-shot (single) optimization or a sequence of optimization using dynamic programming (DP). However, the computation of their global optima often faces NP-hardness, and thus only locally optimal solutions
Externí odkaz:
http://arxiv.org/abs/2409.00655
In this work, we study the system identification problem for parameterized non-linear systems using basis functions under adversarial attacks. Motivated by the LASSO-type estimators, we analyze the exact recovery property of a non-smooth estimator, w
Externí odkaz:
http://arxiv.org/abs/2409.00276
Publikováno v:
ICLR 2023
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience. However, the aspect of constraint violations has not been adequately addressed in the existing works, making their applic
Externí odkaz:
http://arxiv.org/abs/2405.16601
Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the future. We tack
Externí odkaz:
http://arxiv.org/abs/2405.16053
A large fraction of total healthcare expenditure occurs due to end-of-life (EOL) care, which means it is important to study the problem of more carefully incentivizing necessary versus unnecessary EOL care because this has the potential to reduce ove
Externí odkaz:
http://arxiv.org/abs/2403.15099
Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions. Avoiding convergence to these critical points poses a major challenge. This work provides new theoretical insights t
Externí odkaz:
http://arxiv.org/abs/2403.06056
Gradient descent (GD) is crucial for generalization in machine learning models, as it induces implicit regularization, promoting compact representations. In this work, we examine the role of GD in inducing implicit regularization for tensor optimizat
Externí odkaz:
http://arxiv.org/abs/2310.15549
We first raise and tackle a ``time synchronization'' issue between the agent and the environment in non-stationary reinforcement learning (RL), a crucial factor hindering its real-world applications. In reality, environmental changes occur over wall-
Externí odkaz:
http://arxiv.org/abs/2309.14989