Timezone: »
Provably Correct SGD-based Exploration for Linear Bandit
Jialin Dong · Lin Yang
Linear bandits are commonly applied to applications with sequential decision-making, where balancing the exploration and exploitation is of paramount importance. Yet existing approaches, e.g., upper confidence bound (UCB) algorithms, usually suffer from large computation complexity per round, can be overly pessimistic, and usually make sudden updates to the learned policies. In this paper, we take an online stochastic gradient descent (SGD) based approach to perform incremental updates on the estimated parameters. Our approach not only saves memory and computation but also gives smooth update to the learned policy. Theoretically, we prove that our proposed algorithm can achieve $\tilde O(d\sqrt{n})$ regret, where $n$ is the number of total time steps of the algorithm, matching existing near-optimal regret bounds in UCB-type algorithms. Furthermore, our approach does not require the ``diversity'' conditions, which bound the minimum eigenvalues of the covariance matrix, as presented in related literature. We further conduct experiments to demonstrate the consistently superb performance of our algorithms.
Author Information
Jialin Dong (University of California, Los Angeles)
Lin Yang (UCLA)
More from the Same Authors
-
2021 : Gap-Dependent Unsupervised Exploration for Reinforcement Learning »
Jingfeng Wu · Vladimir Braverman · Lin Yang -
2021 : Online Sub-Sampling for Reinforcement Learning with General Function Approximation »
Dingwen Kong · Ruslan Salakhutdinov · Ruosong Wang · Lin Yang -
2021 : Solving Multi-Arm Bandit Using a Few Bits of Communication »
Osama Hanna · Lin Yang · Christina Fragouli -
2022 : Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning »
Dingwen Kong · Lin Yang -
2023 Poster: Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds »
Shengshi Li · Lin Yang -
2023 Poster: Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling »
Yunfan Li · Yiran Wang · Yu Cheng · Lin Yang -
2023 Poster: Does Sparsity Help in Learning Misspecified Linear Bandits? »
Jialin Dong · Lin Yang -
2023 Poster: Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost »
Sanae Amani · Tor Lattimore · Andras Gyorgy · Lin Yang -
2022 Poster: On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning »
Weichao Mao · Lin Yang · Kaiqing Zhang · Tamer Basar -
2022 Spotlight: On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning »
Weichao Mao · Lin Yang · Kaiqing Zhang · Tamer Basar -
2021 : Solving Multi-Arm Bandit Using a Few Bits of Communication »
Osama Hanna · Lin Yang · Christina Fragouli -
2021 Workshop: Workshop on Reinforcement Learning Theory »
Shipra Agrawal · Simon Du · Niao He · Csaba Szepesvari · Lin Yang -
2021 Poster: Provably Correct Optimization and Exploration with Non-linear Policies »
Fei Feng · Wotao Yin · Alekh Agarwal · Lin Yang -
2021 Poster: Randomized Exploration in Reinforcement Learning with General Value Function Approximation »
Haque Ishfaq · Qiwen Cui · Viet Nguyen · Alex Ayoub · Zhuoran Yang · Zhaoran Wang · Doina Precup · Lin Yang -
2021 Spotlight: Provably Correct Optimization and Exploration with Non-linear Policies »
Fei Feng · Wotao Yin · Alekh Agarwal · Lin Yang -
2021 Spotlight: Randomized Exploration in Reinforcement Learning with General Value Function Approximation »
Haque Ishfaq · Qiwen Cui · Viet Nguyen · Alex Ayoub · Zhuoran Yang · Zhaoran Wang · Doina Precup · Lin Yang -
2021 Poster: Safe Reinforcement Learning with Linear Function Approximation »
Sanae Amani · Christos Thrampoulidis · Lin Yang -
2021 Spotlight: Safe Reinforcement Learning with Linear Function Approximation »
Sanae Amani · Christos Thrampoulidis · Lin Yang -
2020 Poster: Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound »
Lin Yang · Mengdi Wang -
2020 Poster: Model-Based Reinforcement Learning with Value-Targeted Regression »
Alex Ayoub · Zeyu Jia · Csaba Szepesvari · Mengdi Wang · Lin Yang -
2020 Poster: Nearly Linear Row Sampling Algorithm for Quantile Regression »
Yi Li · Ruosong Wang · Lin Yang · Hanrui Zhang -
2020 Poster: Obtaining Adjustable Regularization for Free via Iterate Averaging »
Jingfeng Wu · Vladimir Braverman · Lin Yang