New paper proposes language model augmented decision transformer for multi-task offline RL
An arXiv paper introduces a Language Model Augmented Decision Transformer aimed at learning a unified policy from heterogeneous offline datasets that generalizes across tasks in multi-task offline reinforcement learning.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv cs.CL
Language Model Augmented Decision Transformer for Multi-Task Offline Reinforcement Learning