Search Results for author:
Found 5 papers, 3 papers with code
Simple Noisy Environment Augmentation for Reinforcement Learning
Data augmentation is a widely used technique for improving model performance in machine learning, particularly in computer vision and natural language processing.
An Introduction to Machine Unlearning
Removing the influence of a specified subset of training data from a machine learning model may be required to address issues such as privacy, fairness, and data quality.
Offline Deep Reinforcement Learning for Dynamic Pricing of Consumer Credit
We introduce a method for pricing consumer credit using recent advances in offline deep reinforcement learning.
A Multilinear Sampling Algorithm to Estimate Shapley Values
In this work, we propose a new sampling method based on a multilinear extension technique as applied in game theory.
A Baseline for Shapley Values in MLPs: from Missingness to Neutrality
Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
