Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling | Zendy

Huaqing Xiong | Zendy; Tengyu Xu | Zendy; Yingbin Liang | Zendy; Wei Zhang | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling

Author(s) -

Huaqing Xiong,

Tengyu Xu,

Yingbin Liang,

Wei Zhang

Publication year - 2021

Publication title -

proceedings of the aaai conference on artificial intelligence

Language(s) - English

Resource type - Journals

eISSN - 2374-3468

pISSN - 2159-5399

DOI - 10.1609/aaai.v35i12.17252

Subject(s) - temporal difference learning , reinforcement learning , constant (computer programming) , convergence (economics) , rate of convergence , mathematics , sampling (signal processing) , stochastic approximation , function (biology) , markov process , type (biology) , nonlinear system , algorithm , computer science , statistics , artificial intelligence , physics , key (lock) , ecology , computer security , filter (signal processing) , quantum mechanics , evolutionary biology , economics , computer vision , biology , programming language , economic growth

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research