Nanowerk

A topology-based shortcut for predicting atomic charges in MOFs to speed up materials screening

A new topology-based method predicts atomic charges in metal-organic frameworks from bond connectivity alone, making large-scale computational screening practical.
IEEE

VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning

Abstract: Although value decomposition networks and the follow on value-based studies factorizes the joint reward function to individual reward functions for a kind of cooperative multiagent ...
GitHub

EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks

This is the official implementation for EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks. The methodology relies on Shapley values approximations to determine ...
IEEE

Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning

Abstract: A common approach for defining a reward function for multi-objective reinforcement learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as ...