04:00
2026-10-09
machinebrief.com
machine-learning
DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks
A new arXiv paper (arXiv:2610.11085v1) introduces DaCe-DT, an offline multi-task reinforcement learning framework that combines length-gated prompt masking (LGPM), retrieval-augmented prompt construct…