paper-with-me

Papers

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration

2019-11-01 · Andrea Zanette, David Brandfonbrener, Emma Brunskill, Matteo Pirotta, Alessandro Lazaric

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory. In this paper, we introduce an optimistically-initialized variant of the popular randomized least-squares value iteration (RLSVI), a model-free algorithm where exploration is induced by perturbing the least-squares approximation of the action-value function. Under the assumption that the Markov decision process has low-rank transition dynamics, we prove that the frequentist regret of RLSVI is upper-bounded by $\widetilde O(d^2 H^2 \sqrt{T})$ where $ d $ are the feature dimension, $ H $ is the horizon, and $ T $ is the total number of steps. To the best of our knowledge, this is the first frequentist regret analysis for randomized exploration with function approximation.

📄 PDF Abstract BibTeX arXiv:1911.00567

Code (2)

kevin-yu-0602/NeuralUCB_257 pytorch
sauxpa/neural_exploration pytorch

Tasks

Reinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration

2020-10-23 · Priyank Agrawal, Jinglin Chen, Nan Jiang

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (T…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Thompson Sampling

Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning

2021-10-02 · Tong Zhang

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this…

Multi-Armed Banditsregressionreinforcement-learningReinforcement Learning+2

Information Directed Sampling and Bandits with Heteroscedastic Noise

2018-01-29 · Johannes Kirschner, Andreas Krause

In the stochastic bandit problem, the goal is to maximize an unknown function via a sequence of noisy evaluations. Typically, the observation noise is assumed to be independent of the evaluation point and to satisfy a ta…

Bayesian OptimizationThompson Sampling

Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration

2025-01-23 · Yan Chen, Qinxun Bai, Yiteng Zhang, Shi Dong 외

Designing learning agents that explore efficiently in a complex environment has been widely recognized as a fundamental challenge in reinforcement learning. While a number of works have demonstrated the effectiveness of …

Improved Regret of Linear Ensemble Sampling

2024-11-06 · Harin Lee, Min-hwan Oh

In this work, we close the fundamental gap of theory and practice by providing an improved regret bound for linear ensemble sampling. We prove that with an ensemble size logarithmic in $T$, linear ensemble sampling can a…