One-Shot Averaging for Distributed TD($\lambda$) Under Markov Sampling
Abstract
We consider a distributed setup for reinforcement learning, where each agent has a copy of the same Markov Decision Process but transitions are sampled from the corresponding Markov chain independently by each agent. We show that in this setting, we can achieve a linear speedup for TD(), a family of popular methods for policy evaluation, in the sense that agents can evaluate a policy times faster provided the target accuracy is small enough. Notably, this speedup is achieved by ``one shot averaging,'' a procedure where the agents run TD() with Markov sampling independently and only average their results after the final step. This significantly reduces the amount of communication required to achieve a linear speedup relative to previous work.
Cite
@article{arxiv.2403.08896,
title = {One-Shot Averaging for Distributed TD($\lambda$) Under Markov Sampling},
author = {Haoxing Tian and Ioannis Ch. Paschalidis and Alex Olshevsky},
journal= {arXiv preprint arXiv:2403.08896},
year = {2024}
}