Persuading Farsighted Receivers in MDPs: the Power of Honesty.

Martino Bernasconi Matteo Castiglioni Alberto Marchesi Mirco Mutti

Published in: CoRR (2023)

Keyphrases

markov decision processes
reinforcement learning
factored mdps
state space
power consumption
cognitive processes
linear programming
optimal policy
infinite horizon
planning under uncertainty
dec pomdps