Stage-wise conservative linear bandits
A Moradipari, C Thrampoulidis… - Advances in neural …, 2020 - proceedings.neurips.cc
… safety constraints on the linear stochastic bandit problem. Inspired by the earlier work of
Kazerouni et al. (2017); Wu et al. (2016), the type of safety … the classic linear stochastic bandit …
Kazerouni et al. (2017); Wu et al. (2016), the type of safety … the classic linear stochastic bandit …
Safe linear stochastic bandits
K Khezeli, E Bitar - Proceedings of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
… tailored to the safe linear bandit framework. The proposed algorithm, which we call the Safe
Exploration and … 3.2 Safe Linear Bandit Model In what follows, we introduce the framework of …
Exploration and … 3.2 Safe Linear Bandit Model In what follows, we introduce the framework of …
Linear stochastic bandits under safety constraints
S Amani, M Alizadeh… - Advances in Neural …, 2019 - proceedings.neurips.cc
… the bandit’s unknown parameters at every round. In this paper, we formulate a linear stochastic
multiarmed bandit problem with safety … As such, the learner is unable to identify all safe …
multiarmed bandit problem with safety … As such, the learner is unable to identify all safe …
Directional optimism for safe linear bandits
S Hutchinson, B Turan… - … Conference on Artificial …, 2024 - proceedings.mlr.press
… The safe linear bandit problem is a version of the classical stochastic linear bandit problem
… Lastly, we introduce a generalization of the safe linear bandit setting where the constraints …
… Lastly, we introduce a generalization of the safe linear bandit setting where the constraints …
Decentralized multi-agent linear bandits with safety constraints
S Amani, C Thrampoulidis - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
… more challenging, setting of safe bandits. For the recently studied problem of linear bandits
with unknown linear safety constraints, we propose the first safe decentralized algorithm. Our …
with unknown linear safety constraints, we propose the first safe decentralized algorithm. Our …
Safe Linear Bandits over Unknown Polytopes
A Gangrade, T Chen… - The Thirty Seventh Annual …, 2024 - proceedings.mlr.press
… T) bounds on safety violations, thus attaining near Pareto-optimality. Further, when safety is
… These results rely on a novel dual analysis of linear bandits: we argue that DOSS proceeds …
… These results rely on a novel dual analysis of linear bandits: we argue that DOSS proceeds …
Conservative contextual linear bandits
A Kazerouni, M Ghavamzadeh… - Advances in …, 2017 - proceedings.neurips.cc
… In this paper, we study the issue of safety in contextual linear bandits that have application
in … of safety for this class of algorithms. We develop a safe contextual linear bandit algorithm, …
in … of safety for this class of algorithms. We develop a safe contextual linear bandit algorithm, …
Generalized linear bandits with safety constraints
S Amani, M Alizadeh… - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
… An extension to generalized linear bandit models was also introduced … safe linear stochastic
bandit problem with linear constraint. In the same work, we proposed the safe linear bandit …
bandit problem with linear constraint. In the same work, we proposed the safe linear bandit …
Stochastic bandits with linear constraints
A Pacchiano, M Ghavamzadeh… - International …, 2021 - proceedings.mlr.press
… a safe action x0 is absolutely necessary for solving the constrained contextual linear bandit
… However, the assumption of knowing the expected cost of the safe action c0 can be relaxed. …
… However, the assumption of knowing the expected cost of the safe action c0 can be relaxed. …
Exploiting problem geometry in safe linear bandits
… bandit problem where the learner’s actions must satisfy an uncertain linear constraint at all
… Lastly, we introduce a generalization of the safe linear bandit setting where the constraints …
… Lastly, we introduce a generalization of the safe linear bandit setting where the constraints …
相关搜索
- safe linear bandits problem geometry
- stochastic linear bandits
- generalized linear bandits safety constraints
- linear bandits convex loss
- linear bandits theoretical guarantees
- linear bandits regret minimization
- linearly parameterized bandits
- linear bandits experimental design
- linear contextual bandits
- robust linear bandits
- safe linear bandits reinforcement learning
- safe multi armed bandits
- adversarial linear bandits
- safe linear quadratic bandits
- safe linear bandits thompson sampling
- safe linear bandits optimization