Salvato in:
Dettagli Bibliografici
Autori principali: Dongare, Shruti Sadanand, Kharel, Amun, Samuel, Jonathan, Zhou, Xiaona
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.17103
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912442972372992
author Dongare, Shruti Sadanand
Kharel, Amun
Samuel, Jonathan
Zhou, Xiaona
author_facet Dongare, Shruti Sadanand
Kharel, Amun
Samuel, Jonathan
Zhou, Xiaona
contents This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder. The model is designed to improve memory and decision-making capabilities in complex environments. We conducted experiments on Atari-Boxing, Atari-Freeway, Atari-Pong, and Crafter tasks, where TransDreamerV3 demonstrated improved performance over DreamerV3, particularly in the Atari-Freeway and Crafter tasks. While issues in the Minecraft task and limited training across all tasks were noted, TransDreamerV3 displays advancement in world model-based reinforcement learning, leveraging transformer architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TransDreamerV3: Implanting Transformer In DreamerV3
Dongare, Shruti Sadanand
Kharel, Amun
Samuel, Jonathan
Zhou, Xiaona
Machine Learning
Artificial Intelligence
This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder. The model is designed to improve memory and decision-making capabilities in complex environments. We conducted experiments on Atari-Boxing, Atari-Freeway, Atari-Pong, and Crafter tasks, where TransDreamerV3 demonstrated improved performance over DreamerV3, particularly in the Atari-Freeway and Crafter tasks. While issues in the Minecraft task and limited training across all tasks were noted, TransDreamerV3 displays advancement in world model-based reinforcement learning, leveraging transformer architectures.
title TransDreamerV3: Implanting Transformer In DreamerV3
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.17103