Efficient and Optimal Policy Gradient Algorithm for Corrupted Multi-armed Bandits

• URL: http://arxiv.org/abs/2502.14146v1
• Date: Wed, 19 Feb 2025 23:16:18 GMT
• Title: Efficient and Optimal Policy Gradient Algorithm for Corrupted Multi-armed Bandits
• Authors: Jiayuan Liu, Siwei Wang, Zhixuan Fang,
• Abstract summary: We show that SAMBA achieves a state-of-the-art $O(Klog T/Delta) + O(C/Delta)$ regret upper bound. We also conduct simulations to demonstrate the effectiveness of SAMBA.
• Score: 29.845787788972594
• License:
• Abstract: In this paper, we consider the stochastic multi-armed bandits problem with adversarial corruptions, where the random rewards of the arms are partially modified by an adversary to fool the algorithm. We apply the policy gradient algorithm SAMBA to this setting, and show that it is computationally efficient, and achieves a state-of-the-art $O(K\log T/\Delta) + O(C/\Delta)$ regret upper bound, where $K$ is the number of arms, $C$ is the unknown corruption level, $\Delta$ is the minimum expected reward gap between the best arm and other ones, and $T$ is the time horizon. Compared with the best existing efficient algorithm (e.g., CBARBAR), whose regret upper bound is $O(K\log^2 T/\Delta) + O(C)$, we show that SAMBA reduces one $\log T$ factor in the regret bound, while maintaining the corruption-dependent term to be linear with $C$. This is indeed asymptotically optimal. We also conduct simulations to demonstrate the effectiveness of SAMBA, and the results show that SAMBA outperforms existing baselines.

Related papers

• Stochastic Bandits Robust to Adversarial Attacks [33.278131584647745]
  This paper investigates multi-armed bandit algorithms that are robust to adversarial attacks. We study two cases of this model, with or without the knowledge of an attack budget $C$. We devise two types of algorithms with regret bounds having additive or multiplicative $C$ dependence terms.
  arXiv  Detail & Related papers  (2024-08-16T17:41:35Z)
• Best-of-Both-Worlds Algorithms for Linear Contextual Bandits [11.94312915280916]
  We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and adversarial regimes.
  arXiv  Detail & Related papers  (2023-12-24T08:27:30Z)
• Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits [99.86860277006318]
  We consider the problem of combining and learning over a set of adversarial algorithms with the goal of adaptively tracking the best one on the fly. The CORRAL of Agarwal et al. achieves this goal with a regret overhead of order $widetildeO(sqrtd S T)$ where $M$ is the number of base algorithms and $T$ is the time horizon. Motivated by this issue, we propose a new recipe to corral a larger band of bandit algorithms whose regret overhead has only emphlogarithmic dependence on $M$ as long
  arXiv  Detail & Related papers  (2022-02-12T21:55:44Z)
• A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits [118.22458816174144]
  We propose a novel robust elimination-type algorithm that runs in epochs, combines exploration with infrequent switching to select a small subset of actions, and plays each action for multiple time instants. Our algorithm, GP Robust Phased Elimination (RGP-PE), successfully balances robustness to corruptions with exploration and exploitation. We perform the first empirical study of robustness in the corrupted GP bandit setting, and show that our algorithm is robust against a variety of adversarial attacks.
  arXiv  Detail & Related papers  (2022-02-03T21:19:36Z)
• Maillard Sampling: Boltzmann Exploration Done Optimally [11.282341369957216]
  This thesis presents a randomized algorithm for the $K$-armed bandit problem. Maillard sampling (MS) computes the probability of choosing each arm in a closed form. We propose a variant of MS called MS$+$ that improves its minimax bound to $sqrtKTlogK$ without losing the optimality.
  arXiv  Detail & Related papers  (2021-11-05T06:50:22Z)
• Bandits with many optimal arms [68.17472536610859]
  We write $p*$ for the proportion of optimal arms and $Delta$ for the minimal mean-gap between optimal and sub-optimal arms. We characterize the optimal learning rates both in the cumulative regret setting, and in the best-arm identification setting.
  arXiv  Detail & Related papers  (2021-03-23T11:02:31Z)
• Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions [53.77572276969548]
  We show that the C$2$UCB algorithm has the optimal regret bound $tildeO(dsqrtkT + dk)$ for the partition matroid constraints. For general constraints, we propose an algorithm that modifies the reward estimates of arms in the C$2$UCB algorithm.
  arXiv  Detail & Related papers  (2021-01-20T04:29:18Z)
• Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions [91.8283876874947]
  We consider a best arm identification (BAI) problem for Sequential bandits with adversarial corruptions in the fixed-budget setting of T steps. We design a novel randomized algorithm, Probabilistic Shrinking($u$) (PSS($u$)), which is agnostic to the amount of corruptions. We show that when the CPS is sufficiently large, no algorithm can achieve a BAI probability tending to $1$ as $Trightarrow infty$.
  arXiv  Detail & Related papers  (2020-10-15T17:34:26Z)
• Stochastic Bandits with Linear Constraints [69.757694218456]
  We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB)
  arXiv  Detail & Related papers  (2020-06-17T22:32:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.