We consider offline Reinforcement Learning (RL), where the agent does no...
We propose a generalization of the synthetic controls and synthetic
inte...
While standard bandit algorithms sometimes incur high regret, their
perf...
Network interference, where the outcome of an individual is affected by ...
The practicality of reinforcement learning algorithms has been limited d...
Randomized experiments are widely used to estimate causal effects across...
Randomized experiments are widely used to estimate causal effects of pro...
Discretization based approaches to solving online reinforcement learning...
Consider the task of matrix estimation in which a dataset X ∈ℝ^n× m is o...
We consider the problem of dividing limited resources to individuals arr...
We consider the problem of dividing limited resources between a set of a...
There is a conjectured computational-statistical gap in terms of the num...
We introduce the technique of adaptive discretization to design efficien...
We present an efficient algorithm for model-free episodic reinforcement
...
We consider the task of tensor estimation, i.e. estimating a low-rank 3-...
Consider a nonparametric contextual multi-arm bandit problem where each ...