Salvato in:
Dettagli Bibliografici
Autori principali: Gan, Yaozhong, Yan, Renye, Tan, Xiaoyang, Wu, Zhe, Xing, Junliang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.03894
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913380124590080
author Gan, Yaozhong
Yan, Renye
Tan, Xiaoyang
Wu, Zhe
Xing, Junliang
author_facet Gan, Yaozhong
Yan, Renye
Tan, Xiaoyang
Wu, Zhe
Xing, Junliang
contents Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies is constrained. This paper introduces a novel off-policy extension to the original PPO method, christened Transductive Off-policy PPO (ToPPO). Herein, we provide theoretical justification for incorporating off-policy data in PPO training and prudent guidelines for its safe application. Our contribution includes a novel formulation of the policy improvement lower bound for prospective policies derived from off-policy data, accompanied by a computationally efficient mechanism to optimize this bound, underpinned by assurances of monotonic improvement. Comprehensive experimental results across six representative tasks underscore ToPPO's promising performance.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03894
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transductive Off-policy Proximal Policy Optimization
Gan, Yaozhong
Yan, Renye
Tan, Xiaoyang
Wu, Zhe
Xing, Junliang
Machine Learning
Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies is constrained. This paper introduces a novel off-policy extension to the original PPO method, christened Transductive Off-policy PPO (ToPPO). Herein, we provide theoretical justification for incorporating off-policy data in PPO training and prudent guidelines for its safe application. Our contribution includes a novel formulation of the policy improvement lower bound for prospective policies derived from off-policy data, accompanied by a computationally efficient mechanism to optimize this bound, underpinned by assurances of monotonic improvement. Comprehensive experimental results across six representative tasks underscore ToPPO's promising performance.
title Transductive Off-policy Proximal Policy Optimization
topic Machine Learning
url https://arxiv.org/abs/2406.03894