In the current paper we relax the information structure of these classical frameworks by allowing arbitrary information arrivalprocesses.

Somewhat surprisingly, learning in a Markov Decision Process is most often considered under the performance criteria ofconsistency or regret minimization(see e.g.

On the analysis front, we establish lower bounds on the performance that is achievable by any non-anticipating policy in the presence of unknown information flows. We further show that our lower bounds can be achieved through suitable policy design.

Somewhat surprisingly, learning in a Markov Decision Process is most often considered under the performance criteria of consistency or regret minimization (see e.g.

Unfortunately, when we move away from the safe haven of two-agent strictly competitive games, a lot of these regularities disappear.

Unfortunately, when we move away from the safe haven of two-agent strictly competitive games, a lot of these regularities disappear.