paper-with-me

홈 › Papers

Off-Policy Evaluation in Embedded Spaces

2022-03-05 · Jaron J. R. Lee, David Arbour, Georgios Theocharous

Off-policy evaluation methods are important in recommendation systems and search engines, where data collected under an existing logging policy is used to estimate the performance of a new proposed policy. A common approach to this problem is weighting, where data is weighted by a density ratio between the probability of actions given contexts in the target and logged policies. In practice, two issues often arise. First, many problems have very large action spaces and we may not observe rewards for most actions, and so in finite samples we may encounter a positivity violation. Second, many recommendation systems are not probabilistic and so having access to logging and target policy densities may not be feasible. To address these issues, we introduce the featurized embedded permutation weighting estimator. The estimator computes the density ratio in an action embedding space, which reduces the possibility of positivity violations. The density ratio is computed leveraging recent advances in normalizing flows and density ratio estimation as a classification problem, in order to obtain estimates which are feasible in practice.

📄 PDF Abstract BibTeX arXiv:2203.02807

Code (0)

등록된 구현이 없습니다.

Tasks

Density Ratio EstimationOff-policy evaluationRecommendation Systems

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces

2020-02-07 · Bogdan Mazoure, Thang Doan, Tianyu Li, Vladimir Makarenkov 외

We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

2020-10-09 · Paul J. Pritz, Liang Ma, Kin K. Leung

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use s…

Model-based Reinforcement LearningRecommendation Systemsreinforcement-learningReinforcement Learning+1

Jointly-Trained State-Action Embedding for Efficient Reinforcement Learning

2020-09-28 · Paul Julian Pritz, Liang Ma, Kin Leung

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use s…

Model-based Reinforcement LearningRecommendation Systemsreinforcement-learningReinforcement Learning+1

Comparison of Embedded Spaces for Deep Learning Classification

2024-08-03 · Stefan Scholl

Embedded spaces are a key feature in deep learning. Good embedded spaces represent the data well to support classification and advanced techniques such as open-set recognition, few-short learning and explainability. This…

ClassificationDeep LearningOpen Set Learning

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces

2022-12-29 · Saket Tiwari, Omer Gottesman, George Konidaris

Advances in reinforcement learning have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and a…

MuJoCoreinforcement-learningReinforcement Learning (RL)