Machine Heart
Apr 2, 2026 · Artificial Intelligence
Dual Alignment Theory Redefines Cross-Domain Offline RL Transfer
The paper revisits cross-domain offline reinforcement learning, showing that aligning both dynamics and value of source data is essential for effective policy transfer, and introduces the DVDF framework that jointly filters source samples, achieving consistent performance gains across multiple robotic control benchmarks.
DVDFcross-domain transferdynamics alignment
0 likes · 13 min read