Salvato in:
Dettagli Bibliografici
Autori principali: Bedaywi, Mark, Rakhsha, Amin, Farahmand, Amir-massoud
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.08803
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914933688500224
author Bedaywi, Mark
Rakhsha, Amin
Farahmand, Amir-massoud
author_facet Bedaywi, Mark
Rakhsha, Amin
Farahmand, Amir-massoud
contents Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and become inefficient in these tasks. When the transition distributions are given, PID VI was recently introduced to accelerate the convergence of Value Iteration using ideas from control theory. Inspired by this, we introduce PID TD Learning and PID Q-Learning algorithms for the RL setting, in which only samples from the environment are available. We give a theoretical analysis of the convergence of PID TD Learning and its acceleration compared to the conventional TD Learning. We also introduce a method for adapting PID gains in the presence of noise and empirically verify its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PID Accelerated Temporal Difference Algorithms
Bedaywi, Mark
Rakhsha, Amin
Farahmand, Amir-massoud
Machine Learning
Artificial Intelligence
Systems and Control
Optimization and Control
Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and become inefficient in these tasks. When the transition distributions are given, PID VI was recently introduced to accelerate the convergence of Value Iteration using ideas from control theory. Inspired by this, we introduce PID TD Learning and PID Q-Learning algorithms for the RL setting, in which only samples from the environment are available. We give a theoretical analysis of the convergence of PID TD Learning and its acceleration compared to the conventional TD Learning. We also introduce a method for adapting PID gains in the presence of noise and empirically verify its effectiveness.
title PID Accelerated Temporal Difference Algorithms
topic Machine Learning
Artificial Intelligence
Systems and Control
Optimization and Control
url https://arxiv.org/abs/2407.08803