d4rl

Introduces CODS, an iterative critic-guided data selection method for offline reinforcement learning that retains task performance at low data budgets by selecting high-residual transitions over multiple rounds.

本文介绍了一种名为Inverter的神经启发式框架，该框架利用逆学习（Inverse Learning, IL）实现快速高效的规划与控制，在D4RL基准测试和量子门合成上取得了显著改进，推理计算量降低了数个数量级。