Saved in:
Bibliographic Details
Main Author: Hill, Vincent W.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.04699
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910401652850688
author Hill, Vincent W.
author_facet Hill, Vincent W.
contents This work describes a technique for active rejection of multiple independent and time-correlated stochastic disturbances for a nonlinear flexible inverted pendulum with cart system with uncertain model parameters. The control law is determined through deep reinforcement learning, specifically with a continuous actor-critic variant of deep Q-learning known as Deep Deterministic Policy Gradient, while the disturbance magnitudes evolve via independent stochastic processes. Simulation results are then compared with those from a classical control system.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04699
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Reinforcement Learning Control for Disturbance Rejection in a Nonlinear Dynamic System with Parametric Uncertainty
Hill, Vincent W.
Systems and Control
This work describes a technique for active rejection of multiple independent and time-correlated stochastic disturbances for a nonlinear flexible inverted pendulum with cart system with uncertain model parameters. The control law is determined through deep reinforcement learning, specifically with a continuous actor-critic variant of deep Q-learning known as Deep Deterministic Policy Gradient, while the disturbance magnitudes evolve via independent stochastic processes. Simulation results are then compared with those from a classical control system.
title Deep Reinforcement Learning Control for Disturbance Rejection in a Nonlinear Dynamic System with Parametric Uncertainty
topic Systems and Control
url https://arxiv.org/abs/2404.04699