Donglin Wang

RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning

2023 · arXiv (Cornell University)

Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world, they …

Pareto Graph Self-Supervised Learning

2024

In this paper, we study the problem of finding proper tradeoff for graph self-supervised learning. Recently, various self-supervised auxiliary tasks have been proposed to accelerate representation learning in Graph Neural Networks (GNNs). However, existing graph …

Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression

2024 · arXiv (Cornell University)

We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing demonstrations, without …

A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning

2024

Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. So learning robotic tasks from pre-collected data is a promising direction. Agile and …