Zero-Shot Reinforcement Learning via Function Encoders

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ingebrand, Tyler, Zhang, Amy, Topcu, Ufuk
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912284467527680
author Ingebrand, Tyler
Zhang, Amy
Topcu, Ufuk
author_facet Ingebrand, Tyler
Zhang, Amy
Topcu, Ufuk
contents Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current task so that the agent understands how it relates to previously seen tasks. To achieve zero-shot transfer, we introduce the function encoder, a representation learning algorithm which represents a function as a weighted combination of learned, non-linear basis functions. By using a function encoder to represent the reward function or the transition function, the agent has information on how the current task relates to previously seen tasks via a coherent vector representation. Thus, the agent is able to achieve transfer between related tasks at run time with no additional training. We demonstrate state-of-the-art data efficiency, asymptotic performance, and training stability in three RL fields by augmenting basic RL algorithms with a function encoder task representation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17173
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-Shot Reinforcement Learning via Function Encoders
Ingebrand, Tyler
Zhang, Amy
Topcu, Ufuk
Machine Learning
Artificial Intelligence
Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current task so that the agent understands how it relates to previously seen tasks. To achieve zero-shot transfer, we introduce the function encoder, a representation learning algorithm which represents a function as a weighted combination of learned, non-linear basis functions. By using a function encoder to represent the reward function or the transition function, the agent has information on how the current task relates to previously seen tasks via a coherent vector representation. Thus, the agent is able to achieve transfer between related tasks at run time with no additional training. We demonstrate state-of-the-art data efficiency, asymptotic performance, and training stability in three RL fields by augmenting basic RL algorithms with a function encoder task representation.
title Zero-Shot Reinforcement Learning via Function Encoders
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.17173