BriefGPT.xyz
Feb, 2021
基于上下文、离线元强化学习的证明改进——关注与对比学习
Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning
HTML
PDF
Lanqing Li, Yuanhao Huang, Dijun Luo
TL;DR
本文针对离线强化学习中的元学习问题，通过引入任务注意力机制和对比学习目标来提高任务表示的鲁棒性，从而改进了现有算法，并在多个元强化学习基准测试中展示了优越的性能和稳健性。
Abstract
meta-learning
for
offline reinforcement learning
(OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is
→