Discrete-Time Mean Field Control with Environment States

no code implementations • 30 Apr 2021 • Kai Cui, Anam Tahir, Mark Sinzger, Heinz Koeppl

Multi-agent reinforcement learning methods have shown remarkable potential in solving complex multi-agent problems but mostly lack theoretical guarantees.

Multi-agent Reinforcement Learning reinforcement-learning +2

Poisson channel with binary Markov input and average sojourn time constraint

no code implementations • 5 Jan 2021 • Mark Sinzger, Maximilian Gehri, Heinz Koeppl

Determining its capacity is an optimization problem with respect to two parameters: the average sojourn times of the promoter's active (ON) and inactive (OFF) state.