paper-with-me

Papers

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

2021-02-08 · NeurIPS 2021 12 · Kefan Dong, Jiaqi Yang, Tengyu Ma

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOlin), which provably converges to a local maximum with sample complexity that only depends on the sequential Rademacher complexity of the model class. Our results imply novel global or local regret bounds on several concrete settings such as linear bandit with finite or sparse model class, and two-layer neural net bandit. A key algorithmic insight is that optimism may lead to over-exploration even for two-layer neural net model class. On the other hand, for convergence to local maxima, it suffices to maximize the virtual return if the model can also reasonably predict the size of the gradient and Hessian of the real return.

📄 PDF Abstract BibTeX arXiv:2102.04168

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits

2016-10-14 · Tor Lattimore, Csaba Szepesvari

Stochastic linear bandits are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notab…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Thompson Sampling

Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

2025-10-12 · Jiazheng Sun, Weixin Wang, Pan Xu arxiv

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemb…

Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism

2020-06-24 · ICML 2020 1 · Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions are allowed to evolve over time, as long…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits

2020-07-15 · Yunbei Xu, Assaf Zeevi

The principle of optimism in the face of uncertainty is one of the most widely used and successful ideas in multi-armed bandits and reinforcement learning. However, existing optimistic algorithms (primarily UCB and its v…

counterfactualMulti-Armed Banditsregression

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

2023-09-21 · NeurIPS 2023 11

Linear contextual bandits represent a fundamental class of models with numerous real-world applications, and it is critical to develop algorithms that can effectively manage noise with unknown variance, ensuring provable…