Off-policy evaluation for large action spaces via policy convolution
Developing accurate off-policy estimators is crucial for both evaluating and optimizing for
new policies. The main challenge in off-policy estimation is the distribution shift between the …
new policies. The main challenge in off-policy estimation is the distribution shift between the …
Variational weighting for kernel density ratios
Kernel density estimation (KDE) is integral to a range of generative and discriminative tasks
in machine learning. Drawing upon tools from the multidimensional calculus of variations …
in machine learning. Drawing upon tools from the multidimensional calculus of variations …
Off-policy estimation with adaptively collected data: the power of online learning
J Lee, C Ma - arXiv preprint arXiv:2411.12786, 2024 - arxiv.org
We consider estimation of a linear functional of the treatment effect using adaptively
collected data. This task finds a variety of applications including the off-policy evaluation …
collected data. This task finds a variety of applications including the off-policy evaluation …
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
We consider off-policy evaluation (OPE) of deterministic target policies for reinforcement
learning (RL) in environments with continuous action spaces. While it is common to use …
learning (RL) in environments with continuous action spaces. While it is common to use …