Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding.

Siyuan Xu Minghui Zhu Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding. 2025 ICML https://proceedings.mlr.press/v267/xu25ao.html https://openreview.net/forum?id=PFMVVaPCn5 conf/icml/2025 db/conf/icml/icml2025.html#XuZ25