Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme - Archive ouverte HAL Access content directly
Book Sections Year : 2021

Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme

(1) , (2) , (2) , (1)
1
2

Abstract

We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theoretical issues. We then propose a modified scheme called Full Gradient DQN (FG-DQN, for short) that has a sound theoretical basis and compare it with the original scheme on sample problems. We observe a better performance for FG-DQN.
Fichier principal
Vignette du fichier
Full_Gradient_main.pdf (1.29 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03462350 , version 1 (01-12-2021)

Identifiers

Cite

Konstantin Avrachenkov, Vivek S Borkar, Harsh P Dolhare, Kishor Patil. Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme. Alexey Piunovskiy; Yi Zhang. Modern Trends in Controlled Stochastic Processes: Theory and Applications, V.III, 41, Springer International Publishing, pp.192-220, 2021, Emergence, Complexity and Computation, 978-3-030-76928-4. ⟨10.1007/978-3-030-76928-4_10⟩. ⟨hal-03462350⟩
40 View
70 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More