Learning Versatile Skills with Curriculum Masking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Yao, Xie, Zhihui, Lin, Zichuan, Ye, Deheng, Li, Shuai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915002444677120
author Tang, Yao
Xie, Zhihui
Lin, Zichuan
Ye, Deheng
Li, Shuai
author_facet Tang, Yao
Xie, Zhihui
Lin, Zichuan
Ye, Deheng
Li, Shuai
contents Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills. Through extensive experiments, we show that CurrMask exhibits superior zero-shot performance on skill prompting tasks, goal-conditioned planning tasks, and competitive finetuning performance on offline RL tasks. Additionally, our analysis of training dynamics reveals that CurrMask gradually acquires skills of varying complexity by dynamically adjusting its masking scheme.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17744
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Versatile Skills with Curriculum Masking
Tang, Yao
Xie, Zhihui
Lin, Zichuan
Ye, Deheng
Li, Shuai
Machine Learning
Artificial Intelligence
Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills. Through extensive experiments, we show that CurrMask exhibits superior zero-shot performance on skill prompting tasks, goal-conditioned planning tasks, and competitive finetuning performance on offline RL tasks. Additionally, our analysis of training dynamics reveals that CurrMask gradually acquires skills of varying complexity by dynamically adjusting its masking scheme.
title Learning Versatile Skills with Curriculum Masking
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.17744