Zobrazeno 1 - 10
of 201
pro vyhledávání: '"Zhou, Enlu"'
Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization of historical trajectories obtained from previous policies is essential
Externí odkaz:
http://arxiv.org/abs/2403.00675
Stochastic optimal control with unknown randomness distributions has been studied for a long time, encompassing robust control, distributionally robust control, and adaptive control. We propose a new episodic Bayesian approach that incorporates Bayes
Externí odkaz:
http://arxiv.org/abs/2308.08478
Autor:
Wang, Yuhao, Zhou, Enlu
We consider a robust reinforcement learning problem, where a learning agent learns from a simulated training environment. To account for the model mis-specification between this training environment and the real environment due to lack of data, we ad
Externí odkaz:
http://arxiv.org/abs/2305.11300
Autor:
Lin, Yifan, Zhou, Enlu
We consider infinite-horizon Markov Decision Processes where parameters, such as transition probabilities, are unknown and estimated from data. The popular distributionally robust approach to addressing the parameter uncertainty can sometimes be over
Externí odkaz:
http://arxiv.org/abs/2301.11415
Autor:
Wang, Yuhao, Zhou, Enlu
In a fixed budget ranking and Selection (R&S) problem, one aims to identify the best design among a finite number of candidates by efficiently allocating the given computing budget to evaluate design performance. Classical methods for R&S usually ass
Externí odkaz:
http://arxiv.org/abs/2209.11809
In this paper we consider the contextual multi-armed bandit problem for linear payoffs under a risk-averse criterion. At each round, contexts are revealed for each arm, and the decision maker chooses one arm to pull and receives the corresponding rew
Externí odkaz:
http://arxiv.org/abs/2206.12463
We consider stochastic optimization under distributional uncertainty, where the unknown distributional parameter is estimated from streaming data that arrive sequentially over time. Moreover, data may depend on the decision of the time when they are
Externí odkaz:
http://arxiv.org/abs/2202.07581
Autor:
Daulton, Samuel, Cakmak, Sait, Balandat, Maximilian, Osborne, Michael A., Zhou, Enlu, Bakshy, Eytan
Bayesian optimization (BO) is a sample-efficient approach for tuning design parameters to optimize expensive-to-evaluate, black-box performance metrics. In many manufacturing processes, the design parameters are subject to random input noise, resulti
Externí odkaz:
http://arxiv.org/abs/2202.07549
We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\in R^{d\times d}$ from a noisy observation $Y$ using an over-parameterization model.
Externí odkaz:
http://arxiv.org/abs/2202.03535
In many real world problems, we are faced with the problem of selecting the best among a finite number of alternatives, where the best alternative is determined based on context specific information. In this work, we study the contextual Ranking and
Externí odkaz:
http://arxiv.org/abs/2201.07782