The paper introduces RATTL (Risk-Adversarial Total-Reward Learning), a framework that adjusts an agent’s caution based on epistemic uncertainty by using a Bayesian posterior over dynamics and a Wasserstein ambiguity set whose radius depends on that posterior. As evidence accumulates, the radius shrinks, smoothly transitioning the agent’s behavior from worst-case robustness to risk-neutral reward maximization. The authors prove a Safety Sandwich theorem showing RATTL’s value lies between the uninformed robust value and the full-knowledge optimum, and demonstrate the method on a binary-hazard example where the criterion reduces to Conditional Value-at-Risk.
By Deep Kumar Ganguly, Jan Kretinsky
arXiv:2606. 08113v1 Announce Type: new Abstract: A small Wasserstein distance does not certify that a transformation is admissible.
By Lei Luo, Jian Yang
arXiv:2504. 10796v4 Announce Type: replace-cross Abstract: Distributionally robust optimization (DRO) is widely used for decision-making under uncertainty, but its adversarial focus on worst-case loss can lead to overly conservative policies.
By Lukas-Benedikt Fiechtner, Jose Blanchet
arXiv:2602. 20403v2 Announce Type: replace Abstract: We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations.
By Guixian Chen, Salar Fattahi, Soroosh Shafiee
arXiv:2412. 20556v2 Announce Type: replace-cross Abstract: We study distributionally robust optimization (DRO) for robust inference when the worst-case distribution is continuous, leading to significant computational challenges due to the infinite-dimensional nature of the optimization problem.
By Linglingzhi Zhu, Yunqin Zhu, Yao Xie
arXiv:2603. 10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional uncertainty, particularly under heavy tails or rare catastrophic events.
By Yaswanth Chittepu, Ativ Joshi, Rajarshi Bhattacharjee, Scott Niekum
arXiv:2605. 00155v3 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility.
By Yikai Wang, Shang Liu, Jose Blanchet
arXiv:2608. 07433v1 Announce Type: cross Abstract: Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space.
By Zhaoyu Zhu, Rui Gao, Shuang Li
The paper introduces a geometric framework for reinforcement learning that treats policies as mappings into the Wasserstein space of action probabilities. It establishes a Riemannian structure induced by stationary distributions, defines the tangent space of policies, and characterizes geodesics while addressing measurability concerns. The authors formulate a general RL optimization problem, construct a gradient flow via Otto's calculus, compute the gradient and Hessian of the energy, and demonstrate the approach with numerical examples for low‑dimensional problems and neural‑network‑parameterized policies for high‑dimensional settings.
By Mathias Dus (IRMA)
arXiv:2510. 07750v3 Announce Type: replace-cross Abstract: Robust optimization safeguards decisions against uncertainty by optimizing against worst-case scenarios, yet their effectiveness hinges on a prespecified robustness level that is often chosen ad hoc, leading to either insufficient protection or overly conservative and costly solutions.
By Wenbin Zhou, Shixiang Zhu
arXiv:2607. 14407v1 Announce Type: cross Abstract: Many signal processing systems ultimately exist to {act}.
By Osvaldo Simeone
arXiv:2607. 15196v1 Announce Type: cross Abstract: We present a novel viewpoint for uncertainty quantification.
By Raghad Alamri, Michele Caprio, Gavin Brown