Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing

• URL: http://arxiv.org/abs/2502.10826v2
• Date: Mon, 14 Jul 2025 17:33:46 GMT
• Title: Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing
• Authors: J. Jon Ryu, Jeongyeol Kwon, Benjamin Koppe, Kwang-Sung Jun,
• Abstract summary: We consider off-policy selection and learning in contextual bandits, where the learner aims to select or train a reward-maximizing policy.<n>First, we propose a novel off-policy selection method that leverages a new betting-based confidence bound applied to an inverse propensity weight sequence.<n>Second, we propose a novel and generic condition on the optimization objective for off-policy learning that strikes a different balance between bias and variance.
• Score: 14.770703014042537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider off-policy selection and learning in contextual bandits, where the learner aims to select or train a reward-maximizing policy using data collected by a fixed behavior policy. Our contribution is two-fold. First, we propose a novel off-policy selection method that leverages a new betting-based confidence bound applied to an inverse propensity weight sequence. Our theoretical analysis reveals that this method achieves a significantly improved, variance-adaptive guarantee over prior work. Second, we propose a novel and generic condition on the optimization objective for off-policy learning that strikes a different balance between bias and variance. One special case, which we call freezing, tends to induce low variance, which is preferred in small-data regimes. Our analysis shows that it matches the best existing guarantees. In our empirical study, our selection method outperforms existing methods, and freezing exhibits improved performance in small-sample regimes.

Related papers

• A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding [68.43987626137512]
  We propose a principled framework for randomized decision-making based on interval estimates of the quality of each item.<n>We introduce MERIT, an optimization-based method that maximizes the worst-case expected number of top candidates selected.<n>We prove that MERIT satisfies desirable axiomatic properties not guaranteed by existing approaches.
  arXiv  Detail & Related papers  (2025-06-23T19:59:30Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• A Minimaximalist Approach to Reinforcement Learning from Human Feedback [49.45285664482369]
  We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches.
  arXiv  Detail & Related papers  (2024-01-08T17:55:02Z)
• Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems [82.92678837778358]
  preference-based methods have demonstrated substantial success in empirical applications such as InstructGPT. We show how human bias and uncertainty in feedback modelings can affect the theoretical guarantees of these approaches.
  arXiv  Detail & Related papers  (2023-07-24T17:50:24Z)
• Regularizing Second-Order Influences for Continual Learning [39.16131410356833]
  Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data. We dissect the interaction of sequential selection steps within a framework built on influence functions.
  arXiv  Detail & Related papers  (2023-04-20T09:30:35Z)
• Conformal Off-Policy Prediction in Contextual Bandits [54.67508891852636]
  Conformal off-policy prediction can output reliable predictive intervals for the outcome under a new target policy. We provide theoretical finite-sample guarantees without making any additional assumptions beyond the standard contextual bandit setup.
  arXiv  Detail & Related papers  (2022-06-09T10:39:33Z)
• Constrained Variational Policy Optimization for Safe Reinforcement Learning [40.38842532850959]
  Safe reinforcement learning aims to learn policies that satisfy certain constraints before deploying to safety-critical applications. primal-dual as a prevalent constrained optimization framework suffers from instability issues and lacks optimality guarantees. This paper overcomes the issues from a novel probabilistic inference perspective and proposes an Expectation-Maximization style approach to learn safe policy.
  arXiv  Detail & Related papers  (2022-01-28T04:24:09Z)
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction [73.77593805292194]
  We train a separate exploration policy to maximize an approximate upper confidence bound of the critics in an off-policy actor-critic framework. To mitigate the off-policy-ness, we adapt the recently introduced DICE framework to learn a distribution correction ratio for off-policy actor-critic training.
  arXiv  Detail & Related papers  (2021-10-22T22:07:51Z)
• Continuous Mean-Covariance Bandits [39.820490484375156]
  We propose a novel Continuous Mean-Covariance Bandit model to take into account option correlation. In CMCB, there is a learner who sequentially chooses weight vectors on given options and observes random feedback according to the decisions. We propose novel algorithms with optimal regrets (within logarithmic factors) and provide matching lower bounds to validate their optimalities.
  arXiv  Detail & Related papers  (2021-02-24T06:37:05Z)
• State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards [88.30521204048551]
  A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. We show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods.
  arXiv  Detail & Related papers  (2021-02-23T21:07:35Z)
• SOAC: The Soft Option Actor-Critic Architecture [25.198302636265286]
  Methods have been proposed for concurrently learning low-level intra-option policies and high-level option selection policy. Existing methods typically suffer from two major challenges: ineffective exploration and unstable updates. We present a novel and stable off-policy approach that builds on the maximum entropy model to address these challenges.
  arXiv  Detail & Related papers  (2020-06-25T13:06:59Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)

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.