Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts.
Giulia Romano, Andrea Agostini, Francesco Trov, Nicola Gatti, Marcello Restelli
Browse the full IJCAI paper archive.
Giulia Romano, Andrea Agostini, Francesco Trov, Nicola Gatti, Marcello Restelli
Browse the full IJCAI paper archive.