Near-optimal Per-Action Regret Bounds for Sleeping Bandits

• URL: http://arxiv.org/abs/2403.01315v2
• Date: Thu, 30 May 2024 00:18:21 GMT
• Title: Near-optimal Per-Action Regret Bounds for Sleeping Bandits
• Authors: Quan Nguyen, Nishant A. Mehta,
• Abstract summary: We derive near-optimal per-action regret bounds for sleeping bandits. In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(KsqrtTAlnK)$. We extend our results to the setting of bandits with advice from sleeping experts, generalizing EXP4 along the way.
• Score: 8.261117235807607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets. Compared to the minimax $\Omega(\sqrt{TA})$ lower bound, this upper bound contains an extra multiplicative factor of $K\ln{K}$. We address this gap by directly minimizing the per-action regret using generalized versions of EXP3, EXP3-IX and FTRL with Tsallis entropy, thereby obtaining near-optimal bounds of order $O(\sqrt{TA\ln{K}})$ and $O(\sqrt{T\sqrt{AK}})$. We extend our results to the setting of bandits with advice from sleeping experts, generalizing EXP4 along the way. This leads to new proofs for a number of existing adaptive and tracking regret bounds for standard non-sleeping bandits. Extending our results to the bandit version of experts that report their confidences leads to new bounds for the confidence regret that depends primarily on the sum of experts' confidences. We prove a lower bound, showing that for any minimax optimal algorithms, there exists an action whose regret is sublinear in $T$ but linear in the number of its active rounds.

Related papers

• Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds [1.03590082373586]
  We propose and analyze TRAiL, a regret-optimal forced exploration algorithm for linear bandits. TraiL ensures a $Omega(sqrtT)$ growth in the inference quality, measured via the minimum eigenvalue of the design (regressor) matrix. We characterize an $Omega(sqrtT)$ minimax lower bound for any algorithm on the expected regret.
  arXiv  Detail & Related papers  (2024-11-19T01:08:13Z)
• Improved Regret Bounds for Bandits with Expert Advice [16.699381591572163]
  We prove a lower bound of order $sqrtK T ln(N/K)$ for the worst-case regret, where $K$ is the number of actions, $N>K$ the number of experts, and $T$ the time horizon. This matches a previously known upper bound of the same order and improves upon the best available lower bound of $sqrtK T (ln N) / (ln K)$.
  arXiv  Detail & Related papers  (2024-06-24T17:14:31Z)
• Adversarial Multi-dueling Bandits [0.4467766778351321]
  We introduce the problem of regret in adversarial multi-dueling bandits. We introduce a novel algorithm, MiDEX (Multi Dueling EXP3), to learn from such preference feedback.
  arXiv  Detail & Related papers  (2024-06-18T10:28:12Z)
• Adversarial Combinatorial Bandits with Switching Costs [55.2480439325792]
  We study the problem of adversarial bandit with a switching cost $lambda$ for a switch of each selected arm in each round. We derive lower bounds for the minimax regret and design algorithms to approach them.
  arXiv  Detail & Related papers  (2024-04-02T12:15:37Z)
• Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR [58.40575099910538]
  We study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $tau$. We show the minimax CVaR regret rate is $Omega(sqrttau-1AK)$, where $A$ is the number of actions and $K$ is the number of episodes. We show that our algorithm achieves the optimal regret of $widetilde O(tau-1sqrtSAK)$ under a continuity assumption and in general attains a near
  arXiv  Detail & Related papers  (2023-02-07T02:22:31Z)
• Nearly Minimax Algorithms for Linear Bandits with Shared Representation [86.79657561369397]
  We consider the setting where we play $M$ linear bandits with dimension $d$, each for $T$ rounds, and these $M$ bandit tasks share a common $k(ll d)$ dimensional linear representation. We come up with novel algorithms that achieve $widetildeOleft(dsqrtkMT + kMsqrtTright)$ regret bounds, which matches the known minimax regret lower bound up to logarithmic factors.
  arXiv  Detail & Related papers  (2022-03-29T15:27:13Z)
• 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)
• Impact of Representation Learning in Linear Bandits [83.17684841392754]
  We study how representation learning can improve the efficiency of bandit problems. We present a new algorithm which achieves $widetildeO(TsqrtkN + sqrtdkNT)$ regret, where $N$ is the number of rounds we play for each bandit.
  arXiv  Detail & Related papers  (2020-10-13T16:35:30Z)
• 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.