paper-with-me

Papers

A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

2021-01-02 · Minbo Gao, Tianle Xie, Simon S. Du, Lin F. Yang

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low switching cost. This paper focuses on the linear Markov Decision Process (MDP) recently studied in [Yang et al 2019, Jin et al 2020] where the linear function approximation is used for generalization on the large state space. We present the first algorithm for linear MDP with a low switching cost. Our algorithm achieves an $\widetilde{O}\left(\sqrt{d^3H^4K}\right)$ regret bound with a near-optimal $O\left(d H\log K\right)$ global switching cost where $d$ is the feature dimension, $H$ is the planning horizon and $K$ is the number of episodes the agent plays. Our regret bound matches the best existing polynomial algorithm by [Jin et al 2020] and our switching cost is exponentially smaller than theirs. When specialized to tabular MDP, our switching cost bound improves those in [Bai et al 2019, Zhang et al 20020]. We complement our positive result with an $\Omega\left(dH/\log d\right)$ global switching cost lower bound for any no-regret algorithm.

📄 PDF Abstract BibTeX arXiv:2101.00494

Code (0)

등록된 구현이 없습니다.

Tasks

4kRecommendation Systems

Similar Papers 제목 키워드 기반

Online Linear Regression and Its Application to Model-Based Reinforcement Learning

2007-12-01 · NeurIPS 2007 12 · Alexander L. Strehl, Michael L. Littman

We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a model-based approach and show that a special …

Model-based Reinforcement Learningregressionreinforcement-learningReinforcement Learning+1

Risk-aware Stochastic Shortest Path

2022-03-03 · Tobias Meggendorfer

We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present …

Provably Efficient Exploration in Policy Optimization

2019-12-12 · ICML 2020 1 · Qi Cai, Zhuoran Yang, Chi Jin, Zhaoran Wang

While policy-based reinforcement learning (RL) achieves tremendous successes in practice, it is significantly less understood in theory, especially compared with value-based RL. In particular, it remains elusive how to d…

Efficient ExplorationReinforcement LearningReinforcement Learning (RL)

Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium

2020-02-17 · Qiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang

We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games with simultaneous moves. To incorporate function approximation, we consider a family of Markov games whe…

Reinforcement Learning

Adaptive Multi-Goal Exploration

2021-11-23 · Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta 외

We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reaching states to adaptively target goals tha…

Deep Reinforcement Learning