Cooperative Online Learning in Stochastic and Adversarial MDPs. (arXiv:2201.13170v3 [cs.LG] UPDATED)

We study cooperative online learning in stochastic and adversarial Markov
decision process (MDP). That is, in each episode, $m$ agents interact with an
MDP simultaneously and share information in order to minimize their individual
regret. We consider environments with two types of randomness: \emph{fresh} --
where each agent's trajectory is sampled i.i.d, and \emph{non-fresh} -- where
the realization is shared by all agents (but each agent's trajectory is also
affected by its own actions). More precisely, with non-fresh randomness the …

arxiv learning online learning stochastic