Provably Optimal Learning Algorithms for Assistance Games

• URL: http://arxiv.org/abs/2607.08012v1
• Date: Thu, 09 Jul 2026 00:38:42 GMT
• Title: Provably Optimal Learning Algorithms for Assistance Games
• Abstract summary: We provide the first provably efficient learning algorithms for repeated assistance games.<n>We present decentralized algorithms for both an informed human and the assistant.<n>We prove that achieving a regret approximation factor better than $(1-1/e)$ is computationally intractable.
• Score: 60.843021846414956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function. While the informed agent (the human) observes a latent state of the world, the uninformed agent (the assistant) observes only the human's actions. We provide the first provably efficient learning algorithms for repeated assistance games. We introduce the notion of assistance regret: the gap between the cumulative utility of interactions and that of the optimal joint policies in hindsight, which map latent states to action pairs. We present decentralized algorithms for both the human and the assistant that achieve a $(1-1/e)$-approximate assistance regret rate of $\widetilde{O}(T^{3/4})$, with runtime polynomial in the size of the action and state spaces. These algorithms are general; in particular, they accommodate any no-regret algorithm for the assistant. We prove that achieving a regret approximation factor better than $(1-1/e)$ is computationally intractable. Furthermore, we demonstrate how these generic no-regret algorithms can be tailored to a pseudo-decentralized setting -- using a shared random string -- to achieve a rate of $\widetilde{O}(T^{1/2})$, optimal up to logarithmic factors.

Related papers

• Comparator-Adaptive $Φ$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games [43.12477663757647]
  A recent work by Lu et al., [2025] introduces an adaptive algorithm whose regret against a comparator $phi$ depends on a certain sparsity-based complexity measure of $phi$.<n>In this work, we propose a general idea to achieve an even better comparator-adaptive $Phi$-regret bound via much simpler algorithms.
  arXiv  Detail & Related papers  (2025-05-22T20:45:47Z)
• Single-Sample and Robust Online Resource Allocation [14.956072215503797]
  We present a novel Exponential Pricing algorithm for online resource allocation.<n>It is robust to corruptions in the outliers model and the value augmentation model.<n>It operates from conventional approaches that use an online learning algorithm for item pricing.
  arXiv  Detail & Related papers  (2025-05-05T18:48:11Z)
• Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency [52.60557300927007]
  We present a $textbfMA-OSMA$ algorithm to transfer the discrete submodular problem into a continuous optimization.<n>We also introduce a projection-free $textbfMA-OSEA$ algorithm, which effectively utilizes the KL divergence by mixing a uniform distribution.<n>Our algorithms significantly improve the $(frac11+c)$-approximation provided by the state-of-the-art OSG algorithm.
  arXiv  Detail & Related papers  (2025-02-07T15:57:56Z)
• Learning to Play Against Unknown Opponents [9.346742321348366]
  We show how to efficiently construct an optimal learning algorithm when the learning agent is not constrained to no-regret.<n>All these results make use of recently developed machinery that converts the analysis of learning algorithms to the class of corresponding geometric objects known as menus.
  arXiv  Detail & Related papers  (2024-12-24T09:05:06Z)
• Contextual Bandits and Imitation Learning via Preference-Based Active Queries [17.73844193143454]
  We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and receive noisy preference feedback. The learner's objective is two-fold: to minimize the regret associated with the executed actions, while simultaneously, minimizing the number of comparison queries made to the expert.
  arXiv  Detail & Related papers  (2023-07-24T16:36:04Z)
• Provably Efficient Reinforcement Learning via Surprise Bound [66.15308700413814]
  We propose a provably efficient reinforcement learning algorithm (both computationally and statistically) with general value function approximations. Our algorithm achieves reasonable regret bounds when applied to both the linear setting and the sparse high-dimensional linear setting.
  arXiv  Detail & Related papers  (2023-02-22T20:21:25Z)
• Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation [69.0695698566235]
  We study reinforcement learning with linear function approximation and adversarially changing cost functions. We present a computationally efficient policy optimization algorithm for the challenging general setting of unknown dynamics and bandit feedback.
  arXiv  Detail & Related papers  (2023-01-30T17:26:39Z)
• On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure [77.60508571062958]
  We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call predictor) We devise an algorithm OSRL-SC whose sample complexity approaches the lower bound, and scales at most as $H(Glog(delta_G)+ Xlog(delta_H))$, with $X,G,H$ being, respectively, the number of tasks, representations and predictors.
  arXiv  Detail & Related papers  (2022-11-28T08:40:12Z)
• Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback [29.553652241608997]
  We study the class of textitsmooth and strongly monotone games and study optimal no-regret learning therein. We first construct a new bandit learning algorithm and show that it achieves the single-agent optimal regret of $tildeTheta(nsqrtT)$. Our results thus settle this open problem and contribute to the broad landscape of bandit game-theoretical learning.
  arXiv  Detail & Related papers  (2021-12-06T08:27:54Z)
• Online Sub-Sampling for Reinforcement Learning with General Function Approximation [111.01990889581243]
  In this paper, we establish an efficient online sub-sampling framework that measures the information gain of data points collected by an RL algorithm. For a value-based method with complexity-bounded function class, we show that the policy only needs to be updated for $proptooperatornamepolylog(K)$ times. In contrast to existing approaches that update the policy for at least $Omega(K)$ times, our approach drastically reduces the number of optimization calls in solving for a policy.
  arXiv  Detail & Related papers  (2021-06-14T07:36:25Z)
• Online Apprenticeship Learning [58.45089581278177]
  In Apprenticeship Learning (AL), we are given a Markov Decision Process (MDP) without access to the cost function. The goal is to find a policy that matches the expert's performance on some predefined set of cost functions. We show that the OAL problem can be effectively solved by combining two mirror descent based no-regret algorithms.
  arXiv  Detail & Related papers  (2021-02-13T12:57:51Z)

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.