English
Related papers

Related papers: Faster Rates for Policy Learning

200 papers

We consider the random design regression model with square loss. We propose a method that aggregates empirical minimizers (ERM) over appropriately chosen random subsets and reduces to ERM in the extreme case, and we establish sharp oracle…

Statistics Theory · Mathematics 2017-07-04 Alexander Rakhlin , Karthik Sridharan , Alexandre B. Tsybakov

Performance of adaptive control policies is assessed through the regret with respect to the optimal regulator, which reflects the increase in the operating cost due to uncertainty about the dynamics parameters. However, available results in…

Systems and Control · Computer Science 2020-03-24 Mohamad Kazem Shirani Faradonbeh , Ambuj Tewari , George Michailidis

We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret…

Computer Science and Game Theory · Computer Science 2023-03-20 Yu-Guan Hsieh , Kimon Antonakopoulos , Volkan Cevher , Panayotis Mertikopoulos

An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and…

Machine Learning · Statistics 2016-07-14 Marek Petrik , Yinlam Chow , Mohammad Ghavamzadeh

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Machine Learning · Computer Science 2019-11-27 Kaixiang Lin , Jiayu Zhou

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

This work addresses the mediator feedback problem, a bandit game where the decision set consists of a number of policies, each associated with a probability distribution over a common space of outcomes. Upon choosing a policy, the learner…

Machine Learning · Computer Science 2024-02-19 Khaled Eldowa , Nicolò Cesa-Bianchi , Alberto Maria Metelli , Marcello Restelli

We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a substantially stronger requirement that achieving…

Machine Learning · Computer Science 2019-11-12 Daron Anderson , Douglas J. Leith

On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between…

Robotics · Computer Science 2019-07-10 Jonathan N. Lee , Michael Laskey , Ajay Kumar Tanwani , Anil Aswani , Ken Goldberg

We consider a setting where a system learns to rank a fixed set of $m$ items. The goal is produce good item rankings for users with diverse interests who interact online with the system for $T$ rounds. We consider a novel top-$1$ feedback…

Machine Learning · Computer Science 2016-08-24 Sougata Chaudhuri , Ambuj Tewari

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

We study a variant of decision-theoretic online learning in which the set of experts that are available to Learner can shrink over time. This is a restricted version of the well-studied sleeping experts problem, itself a generalization of…

Machine Learning · Computer Science 2019-10-31 Hamid Shayestehmanesh , Sajjad Azami , Nishant A. Mehta

This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…

Machine Learning · Computer Science 2022-08-23 Mohamad Kazem Shirani Faradonbeh

We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision…

Machine Learning · Computer Science 2015-03-02 Wouter M. Koolen , Tim van Erven

Obtaining first-order regret bounds -- regret bounds scaling not as the worst-case but with some measure of the performance of the optimal policy on a given instance -- is a core question in sequential decision-making. While such bounds…

Machine Learning · Computer Science 2022-10-24 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

We demonstrate that, in the classical non-stochastic regret minimization problem with $d$ decisions, gains and losses to be respectively maximized or minimized are fundamentally different. Indeed, by considering the additional sparsity…

Machine Learning · Computer Science 2015-11-30 Joon Kwon , Vianney Perchet

Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using the posterior class probabilities and misclassification…

Machine Learning · Computer Science 2025-03-25 Alexandre Perez-Lebel , Gael Varoquaux , Sanmi Koyejo , Matthieu Doutreligne , Marine Le Morvan

We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action on the basis of a context and receives reward for the…

Machine Learning · Computer Science 2016-02-09 Vasilis Syrgkanis , Akshay Krishnamurthy , Robert E. Schapire