文章基本信息

标题：Content Classification Tasks with Data Preprocessing Manifestations
本地全文：下载
作者：Mamoona Anam ; Kantilal P. Rane ; Ali Alenezi 等
期刊名称：Webology
印刷版ISSN：1735-188X
出版年度：2022
卷号：19
期号：1
页码：1413-1430
DOI：10.14704/WEB/V19I1/WEB19094
语种：English
出版社：University of Tehran
摘要：Deep reinforcement learning has a major hurdle in terms of data efficiency. We solve this challenge by pretraining an encoder with unlabeled input, which is subsequently finetuned on a tiny quantity of task-specific input. We use a mixture of latent dynamics modelling and unsupervised goal-conditioned RL to encourage learning representations that capture various elements of the underlying MDP. Our approach significantly outperforms previous work combining offline representation pretraining with task-specific finetuning when limited to 100k steps of interaction on Atari games (equivalent to two hours of human experience) and compares favourably with other pretraining methods that require orders of magnitude more data. When paired with larger models and more diverse, task-aligned observational data, our methodology shows great promise, nearing human-level performance and data efficiency on Atari in the best-case scenario.
关键词：Content Classification;Tasks with Data;Manifestations;Human Experience;Deep Reinforcement Learning;Self-supervised Learning (SSL);SPR;Goal-conditioned RL and Inverse Modelling