Higher-Order Action Supervision Makes A Strong Policy Class

The paper proposes a new loss scheme that simultaneously supervises zeroth- and first-order actions to improve policy performance and control robustness in data-driven decision-making methods such as imitation learning and reinforcement learning. The approach provides formal theoretical guarantees, works with any off-the-shelf policy model, and can be added as a lightweight plug‑and‑play module to existing offline RL frameworks. Experiments on OGBench and D4RL show significant gains in performance, robustness, and out‑of‑distribution generalization, especially in low‑data settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• reinforcement-learning
• robotics