FedWB aggregates local models by computing Wasserstein barycenters of flattened, normalized weight matrices, yielding faster early convergence than FedAvg on MNIST and on heterogeneous CartPole DQN training.
Reinforcement learning from simulated environments: An encoder decoder framework
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters
FedWB aggregates local models by computing Wasserstein barycenters of flattened, normalized weight matrices, yielding faster early convergence than FedAvg on MNIST and on heterogeneous CartPole DQN training.