The paper proves that personalized federated temporal-difference learning with a shared linear representation converges at rate O(1/(N^{2/3} T^{2/3})), yielding linear speedup in the number of agents under Markovian noise.
When the state and action spaces are large, it is com- putationally infeasible to store Qi,πi (s, a) for all state-action pairs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
The paper proves that personalized federated temporal-difference learning with a shared linear representation converges at rate O(1/(N^{2/3} T^{2/3})), yielding linear speedup in the number of agents under Markovian noise.