paper-with-me

Papers

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

2020-12-14 · Andrea Zanette

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy or to 2) estimate the value of a target policy. For both tasks we derive \emph{exponential} information-theoretic lower bounds in discounted infinite horizon MDPs with a linear function representation for the action value function even if 1) \emph{realizability} holds, 2) the batch algorithm observes the exact reward and transition \emph{functions}, and 3) the batch algorithm is given the \emph{best} a priori data distribution for the problem class. Our work introduces a new `oracle + batch algorithm' framework to prove lower bounds that hold for every distribution. The work shows an exponential separation between batch and online reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2012.08005

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Gaussian Process Bandit Optimization with Few Batches

2021-10-15 · Zihan Li, Jonathan Scarlett

In this paper, we consider the problem of black-box optimization using Gaussian Process (GP) bandit optimization with a small number of batches. Assuming the unknown function has a low norm in the Reproducing Kernel Hilb…

Minimization of Stochastic First-order Oracle Complexity of Adaptive Methods for Nonconvex Optimization

2021-12-14 · Hideaki Iiduka

Numerical evaluations have definitively shown that, for deep learning optimizers such as stochastic gradient descent, momentum, and adaptive methods, the number of steps needed to train a deep neural network halves for e…

Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally

2023-05-03 · Konstantinos E. Nikolakakis, Amin Karbasi, Dionysis Kalogerias

We establish matching upper and lower generalization error bounds for mini-batch Gradient Descent (GD) training with either deterministic or stochastic, data-independent, but otherwise arbitrary batch selection rules. We…

All

Batched Kernelized Bandits: Refinements and Extensions

2026-03-13 · Chenkai Ma, Keqin Chen, Jonathan Scarlett arxiv

In this paper, we consider the problem of black-box optimization with noisy feedback revealed in batches, where the unknown function to optimize has a bounded norm in some Reproducing Kernel Hilbert Space (RKHS). We refe…

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

2020-11-08 · Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári 외

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on t…

feature selectionModel Selectionreinforcement-learningReinforcement Learning+1