Guardado en:
Detalles Bibliográficos
Autores principales: Gan, Yaozhong, Yan, Renye, Wu, Zhe, Xing, Junliang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.03678
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929376010960896
author Gan, Yaozhong
Yan, Renye
Wu, Zhe
Xing, Junliang
author_facet Gan, Yaozhong
Yan, Renye
Wu, Zhe
Xing, Junliang
contents On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy Optimization (RPO), a novel on-policy extension that amalgamates past and future state-action information for policy optimization. This approach empowers the agent for introspection, allowing modifications to its actions within the current state. Theoretical analysis confirms that policy performance is monotonically improved and contracts the solution space, consequently expediting the convergence procedure. Empirical results demonstrate RPO's feasibility and efficacy in two reinforcement learning benchmarks, culminating in superior sample efficiency. The source code of this work is available at https://github.com/Edgargan/RPO.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reflective Policy Optimization
Gan, Yaozhong
Yan, Renye
Wu, Zhe
Xing, Junliang
Machine Learning
Artificial Intelligence
On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy Optimization (RPO), a novel on-policy extension that amalgamates past and future state-action information for policy optimization. This approach empowers the agent for introspection, allowing modifications to its actions within the current state. Theoretical analysis confirms that policy performance is monotonically improved and contracts the solution space, consequently expediting the convergence procedure. Empirical results demonstrate RPO's feasibility and efficacy in two reinforcement learning benchmarks, culminating in superior sample efficiency. The source code of this work is available at https://github.com/Edgargan/RPO.
title Reflective Policy Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.03678