A federated actor-critic framework lets agents share a linear subspace representation for policies while maintaining personalized local actors and critics, achieving critic error and policy gradient convergence rates of order 1 over square root of TK with linear speedup in K agents under environment
Finite-time analysis of on-policy heterogeneous federated reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Federated Q-learning in heterogeneous environments achieves linear speedup in K agents for sampling error but is limited to Θ(E/T) convergence when averaging every E steps, with a two-phase error decay-then-rise behavior in experiments.
citing papers explorer
-
Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
A federated actor-critic framework lets agents share a linear subspace representation for policies while maintaining personalized local actors and critics, achieving critic error and policy gradient convergence rates of order 1 over square root of TK with linear speedup in K agents under environment
-
On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments
Federated Q-learning in heterogeneous environments achieves linear speedup in K agents for sampling error but is limited to Θ(E/T) convergence when averaging every E steps, with a two-phase error decay-then-rise behavior in experiments.