← 研踪 PaperTrailarXiv:2611.22759 · v1
Robust Actor-Critic Learning under Transport and Divergence Uncertainty
首次提交 2026-11-17 21:26
版本更新 2026-11-17 21:26
雷达观测 2026-11-18 19:41
摘要
Learning reliable control policies requires accounting for uncertainty in transition dynamics and errors introduced by function estimation and action generation. We develop an actor--critic method for discounted robust Markov decision processes with continuous states and actions and an unknown nominal transition law. We consider transition uncertainty sets defined by Wasserstein distance, total variation, Kullback--Leibler divergence, or Pearson chi-square divergence. A conditional diffusion model is fitted once to offline transitions. At each subsequent iteration, we estimate the robust action-value function from current-policy observations using a shared-target minimax criterion, then update a generative actor through exponentially weighted score matching. Regularization preserves exploration and provides the density regularity needed for conditional distribution estimation. Under coverage and regularity conditions, we establish finite-sample bounds for critic estimation, the learned conditional action law, and the robust return of the implemented policy. The bounds distinguish critic estimation error, uncertainty in the nominal transition model, and policy regularization, and characterize how the four robustness radii affect the resulting guarantees.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 21:26 · 最新观测版本
Robust Actor-Critic Learning under Transport and Divergence Uncertainty
Learning reliable control policies requires accounting for uncertainty in transition dynamics and errors introduced by function estimation and action generation. We develop an actor--critic method for discounted robust Markov decision processes with continuous states and actions and an unknown nominal transition law. We consider transition uncertainty sets defined by Wasserstein distance, total variation, Kullback--Leibler divergence, or Pearson chi-square divergence. A conditional diffusion model is fitted once to offline transitions. At each subsequent iteration, we estimate the robust action-value function from current-policy observations using a shared-target minimax criterion, then update a generative actor through exponentially weighted score matching. Regularization preserves exploration and provides the density regularity needed for conditional distribution estimation. Under coverage and regularity conditions, we establish finite-sample bounds for critic estimation, the learned conditional action law, and the robust return of the implemented policy. The bounds distinguish critic estimation error, uncertainty in the nominal transition model, and policy regularization, and characterize how the four robustness radii affect the resulting guarantees.
查看此版本解读 →查看此版本原文 ↗