Equivariant Graph-Representation-Based Actor-Critic Reinforcement Learning for Nanoparticle Design.

Jonas Elsborg Arghya Bhowmik

Published in: J. Chem. Inf. Model. (2023)

Keyphrases

graph representation
reinforcement learning
actor critic
function approximation
graph model
temporal difference
reinforcement learning algorithms
machine learning
state space
learning algorithm
feature vectors
semi supervised
average reward
policy gradient
approximate dynamic programming