Login / Signup
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts.
Giulia Romano
Andrea Agostini
Francesco Trovò
Nicola Gatti
Marcello Restelli
Published in:
IJCAI (2022)
Keyphrases
</>
spatio temporal
markov decision processes
learning algorithm
reinforcement learning
temporal information
feedback mechanisms
computer vision
relevance feedback
multiarmed bandit
multi agent
visual feedback
information systems
video sequences
recommender systems
bandit problems