The Flow has not summarised this story yet — read it at arXiv Machine Learning.
In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We address both forms of uncertainty as a first st...
arXiv:2602. 23545v2 Announce Type: replace Abstract: In the real world, planning is often challenged by distribution shifts.
arXiv:2608. 02519v1 Announce Type: new Abstract: Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty.
Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable.
arXiv:2602. 03778v2 Announce Type: replace-cross Abstract: Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events.
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.