Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning

no code implementations • 22 Feb 2021 • Lanqing Li, Yuanhao Huang, Mingzhe Chen, Siteng Luo, Dijun Luo, Junzhou Huang

Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications.

Contrastive Learning Meta-Learning +3