Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations

1 code implementation • 26 Dec 2023 • Renzhe Zhou, Chen-Xiao Gao, Zongzhang Zhang, Yang Yu

GENTLE employs Task Auto-Encoder~(TAE), which is an encoder-decoder architecture to extract the characteristics of the tasks.

Contrastive Learning Decoder +3