3 papers
cs.LG2025
PEnGUiN: Partially Equivariant Graph NeUral Networks for Sample Efficient MARL
Joshua McClellan, Greyson Brothers, Furong Huang +1
Equivariant Graph Neural Networks (EGNNs) have emerged as a promising approach in Multi-Agent Reinforcement Learning (MARL), leveraging symmetry guarantees to greatly improve sampl…
cs.LG2024
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
Joshua McClellan, Naveed Haghani, John Winder +2
Multi-Agent Reinforcement Learning (MARL) struggles with sample inefficiency and poor generalization [1]. These challenges are partially due to a lack of structure or inductive bia…
cs.LG2023
Adaptive Neural Networks Using Residual Fitting
Noah Ford, John Winder, Josh McClellan
Current methods for estimating the required neural-network size for a given problem class have focused on methods that can be computationally intensive, such as neural-architecture…