Search Results for author:
Found 2 papers, 0 papers with code
Multi-Armed Bandits with Generalized Temporally-Partitioned Rewards
In some real-world applications, feedback about a decision is delayed and may arrive via partial rewards that are observed with different delays.
Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards
In this paper, we introduce a general formulation of how an arm's cumulative reward is distributed across several rounds, called Beta-spread property.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
