1.1k citations · 1.9k across the 55 of their papers we have counts for
55 papers
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes
Cyrille Kone, Kevin Jamieson
We study the -PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finite-time guarantees for appro…
Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning
Harin Lee, Kevin Jamieson
We study reinforcement learning with delayed state observation, where the agent observes the current state after some random number of time steps. We propose an algorithm that comb…
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
Zhihan Xiong, Romain Camilleri, Maryam Fazel +2
We investigate the fixed-budget best-arm identification (BAI) problem for linear bandits in a potentially non-stationary environment. Given a finite arm set $\mathcal{X}\subset\mat…
Demonstrating Large-Scale Package Manipulation via Learned Metrics of Pick Success
Shuai Li, Azarakhsh Keipour, Kevin Jamieson +3
Automating warehouse operations can reduce logistics overhead costs, ultimately driving down the final price for consumers, increasing the speed of delivery, and enhancing the resi…
Optimal Exploration for Model-Based RL in Nonlinear Systems
Andrew Wagenmaker, Guanya Shi, Kevin Jamieson
Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory. A commonly applied approach is to first explore the e…
Active Representation Learning for General Task Space with Applications in Robotics
Yifang Chen, Yingbing Huang, Simon S. Du +2
Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal r…
Improved Active Multi-Task Representation Learning via Lasso
Yiping Wang, Yifang Chen, Kevin Jamieson +1
To leverage the copious amount of data from source tasks and overcome the scarcity of the target task samples, representation learning based on multi-task pretraining has become a…
On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff
This paper studies a variant of two-player zero-sum matrix games, where, at each timestep, the row player selects row , the column player selects column , and the row player…
Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games
Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff
We study the sample complexity of identifying an approximate equilibrium for two-player zero-sum matrix games. That is, in a sequence of repeated game plays, how many r…
Instance-optimal PAC Algorithms for Contextual Bandits
Zhaoqi Li, Lillian Ratliff, Houssam Nassif +2
In the stochastic contextual bandit setting, regret-minimizing algorithms have been extensively researched, but their instance-minimizing best-arm identification counterparts remai…
Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design
Andrew Wagenmaker, Kevin Jamieson
While much progress has been made in understanding the minimax sample complexity of reinforcement learning (RL) -- the complexity of learning on the "worst-case" instance -- such m…
Active Learning with Safety Constraints
Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern +2
Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world deci…
Active Multi-Task Representation Learning
Yifang Chen, Simon S. Du, Kevin Jamieson
To leverage the power of big data from source tasks and overcome the scarcity of the target task samples, representation learning based on multi-task pretraining has become a stand…
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
Andrew Wagenmaker, Yifang Chen, Max Simchowitz +2
Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy f…
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Andrew Wagenmaker, Yifang Chen, Max Simchowitz +2
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 q…
Best Arm Identification with Safety Constraints
Zhenlin Wang, Andrew Wagenmaker, Kevin Jamieson
The best arm identification problem in the multi-armed bandit setting is an excellent model of many real-world decision-making problems, yet it fails to capture the fact that in th…
Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers
Julian Katz-Samuels, Blake Mason, Kevin Jamieson +1
We consider interactive learning in the realizable setting and develop a general framework to handle problems ranging from best arm identification to active classification. We begi…
Nearly Optimal Algorithms for Level Set Estimation
Blake Mason, Romain Camilleri, Subhojyoti Mukherjee +3
The level set estimation problem seeks to find all points in a domain where the value of an unknown function exceeds a threshold .…
Selective Sampling for Online Best-arm Identification
Romain Camilleri, Zhihan Xiong, Maryam Fazel +2
This work considers the problem of selective-sampling for best-arm identification. Given a set of potential options , a learner aims to compute with…
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson
The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying -optimal policies. While a simple reduction allows one to app…
Corruption Robust Active Learning
Yifang Chen, Simon S. Du, Kevin Jamieson
We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the lear…
Improved Algorithms for Agnostic Pool-based Active Classification
Julian Katz-Samuels, Jifan Zhang, Lalit Jain +1
We consider active learning for binary classification in the agnostic pool-based setting. The vast majority of works in active learning in the agnostic setting are inspired by the…
High-Dimensional Experimental Design and Kernel Bandits
Romain Camilleri, Julian Katz-Samuels, Kevin Jamieson
In recent years methods from optimal linear experimental design have been leveraged to obtain state of the art results for linear bandits. A design returned from an objective such…
Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Yifang Chen, Simon S. Du, Kevin Jamieson
We study episodic reinforcement learning under unknown adversarial corruptions in both the rewards and the transition probabilities of the underlying system. We propose new algorit…