Tootfinder

This https://arxiv.org/abs/2401.10240 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Policy Evaluation in Distributional LQR (Extended Version)
Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard reinforcement learning. Meanwhile, a challenge in DRL is that the policy evaluation typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for the special class of DRL problems t…

Thus far, the Supreme Court’s rulings in both the 14th Amendment and presidential immunity case have helped to reinforce Trump’s narrative that these criminal indictments aren’t really about him, they are about his legions of MAGA followers.
In equating his problems with their problems, Trump has ample fodder
— bogus as it may be
— to once again argue that his legal troubles are not of his own doing, but rather, the work of political adversaries who have been conspiring to i…

A criminologist explains why half of America does not care about Trump's crimes
Since 2023, when Donald Trump was criminally indicted in a combined four criminal cases on 91 felony counts, I have repeatedly been asked to explain how one-half of the American public seemingly does not care about the alleged crimes committed by their former president and presumptive 2024 Republica...

This https://arxiv.org/abs/2402.16543 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Model-based deep reinforcement learning for accelerated learning from flow simulations
In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms. While reinforcement learning has been applied successfully in a number of rather simple flow control benchmarks, a ma…