On solutions of the distributional Bellman equation
In distributional reinforcement learning (RL), not only expected returns but the complete return distributions of a policy are taken into account. The return distribution for a fixed policy is given as the solution of an associated distributional Bellman equation. In this note, we consider general d...
Main Authors: | Julian Gerstenberg, Ralph Neininger, Denis Spiegel |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2023-06-01
|
Series: | Electronic Research Archive |
Subjects: | |
Online Access: | https://www.aimspress.com/article/doi/10.3934/era.2023228?viewType=HTML |
Similar Items
-
A Study on Numerical Solutions of Hamilton-Jacobi-Bellman Equations Based on Successive Approximation Approach
by: Ichiro Maruta, et al.
Published: (2020-05-01) -
Nonlinear dynamic inequalities of Gronwall-Bellman type on time scales
by: Samir Saker
Published: (2011-11-01) -
Research on Reinforcement Learning Algorithm-Based Practical Teaching and Reform Oriented to Enhancement of College Students’ Vocational Ability in Colleges and Universities
by: Hu Yuzi, et al.
Published: (2024-01-01) -
A Generalized Finite Difference Method for Solving Hamilton–Jacobi–Bellman Equations in Optimal Investment
by: Jiamian Lin, et al.
Published: (2023-05-01) -
Reform and Innovation of Civic and Political Education Based on Deep Enhanced Learning Methods
by: Cui Chen
Published: (2024-01-01)