Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning

1 code implementation • 28 May 2024 • Xinran Li, Zifan Liu, Shibo Chen, Jun Zhang

In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments.

AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis

no code implementations • 18 Dec 2022 • Zifan Liu, Evan Rosen, Paul Suganthan G. C

Automated slicing aims to identify subsets of evaluation data where a trained model performs anomalously.

Fairness

Picket: Guarding Against Corrupted Data in Tabular Data during Learning and Inference

1 code implementation • 8 Jun 2020 • Zifan Liu, Zhechun Zhou, Theodoros Rekatsinas

Picket is designed as a plugin that can increase the robustness of any machine learning pipeline.

BIG-bench Machine Learning Outlier Detection

On Robust Mean Estimation under Coordinate-level Corruption

no code implementations • 10 Feb 2020 • Zifan Liu, Jongho Park, Theodoros Rekatsinas, Christos Tzamos

We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions.

Matrix Completion