Reversing PPO's update order in federated learning, actor before critic, removes the pairwise critic-difference term from the convergence bound and improves performance on heterogeneous control tasks.
Linear off-policy actor-critic
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning
Reversing PPO's update order in federated learning, actor before critic, removes the pairwise critic-difference term from the convergence bound and improves performance on heterogeneous control tasks.