FedRQ adds a robustness term to federated Q-learning and claims convergence to an optimal worst-case policy over heterogeneous local environments, but the proof has a reversed inequality.
Fedkl: Tackling data heterogeneity in fed- erated reinforcement learning by penalizing kl divergence,
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
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Federated Reinforcement Learning in Heterogeneous Environments
FedRQ adds a robustness term to federated Q-learning and claims convergence to an optimal worst-case policy over heterogeneous local environments, but the proof has a reversed inequality.