# Stochastic Bandits with Delayed Composite Anonymous Feedback

arXiv: https://arxiv.org/abs/1910.01161 · HTML: https://mlsanity.com/paper/1910.01161/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Dynamical Linear Bandits](https://mlsanity.com/paper/2211.08997/) (2022)
- [Smooth Sequential Optimisation with Delayed Feedback](https://mlsanity.com/paper/2106.11294/) (2021)
- [Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback](https://mlsanity.com/paper/2303.13604/) (2023)
- [Stochastic Contextual Bandits with Long Horizon Rewards](https://mlsanity.com/paper/2302.00814/) (2023)
- [Sales Channel Optimization via Simulations Based on Observational Data with Delayed Rewards: A Case Study at LinkedIn](https://mlsanity.com/paper/2209.07749/) (2022)
- [Linear and Neural Dueling Bandits with Delayed Feedback](https://mlsanity.com/paper/2605.26554/) (2026)

## Abstract (arXiv)

We explore a novel setting of the Multi-Armed Bandit (MAB) problem inspired from real world applications which we call bandits with "stochastic delayed composite anonymous feedback (SDCAF)". In SDCAF, the rewards on pulling arms are stochastic with respect to time but spread over a fixed number of time steps in the future after pulling the arm. The complexity of this problem stems from the anonymous feedback to the player and the stochastic generation of the reward. Due to the aggregated nature of the rewards, the player is unable to associate the reward to a particular time step from the past. We present two algorithms for this more complicated setting of SDCAF using phase based extensions of the UCB algorithm. We perform regret analysis to show sub-linear theoretical guarantees on both the algorithms.