Tootfinder

Private Astronautenmission zurück auf der Erde
Nach zwei Wochen an Bord der Internationalen Raumstation ISS sind vier Raumfahrer der Axiom-4-Crew zurück auf der Erde. Die Mission brachte viele Premieren.
https://www.…

Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
Mani Hamidi, Terrence W. Deacon
https://arxiv.org/abs/2507.11482 https://

Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
Three core tenets of reinforcement learning (RL)--concerning the definition of agency, the objective of learning, and the scope of the reward hypothesis--have been highlighted as key targets for conceptual revision, with major implications for theory and application. We propose a framework, inspired by open-ended evolutionary theory, to reconsider these three "dogmas." We revisit each assumption and address related concerns raised alongside them. To make our arguments relevant to RL as a model …

Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
Shunpeng Yang, Zhen Fu, Zhefeng Cao, Guo Junde, Patrick Wensing, Wei Zhang, Hua Chen
https://arxiv.org/abs/2506.11470

Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified framework combining a morphology-agnostic generative diffusion model with a lightweight residual policy optimized via reinforcement learning (RL). The diffusion model captures morphology-invariant locomotion patterns from diverse cross-embodiment datasets, improving…

On Universal Deformations of Compressible Cauchy Elastic Solids Reinforced by Inextensible Fibers
Arash Yavari
https://arxiv.org/abs/2506.11203 https://

On Universal Deformations of Compressible Cauchy Elastic Solids Reinforced by Inextensible Fibers
Universal deformations are those that can be maintained in the absence of body forces and by applying only boundary tractions, for all materials within a given constitutive class. We study the universal deformations of compressible isotropic Cauchy elastic solids reinforced by a single family of inextensible fibers. We consider straight fibers parallel to the Cartesian Z-axis in the reference configuration and derive the universality constraints. The principal invariants of the right Cauchy-Gre…

Ecuador: Stop land grabbing and racial discrimination for palm oil! https://www.rainforest-rescue.org/petitions/1270/ecuador-stop-land-grabbing-and-racial-discrimination-for-palm-oil

#petition Ecuador: Stop land grabbing and racial discrimination for palm oil!
Communities in northern Ecuador are fighting back against land grabbing and deforestation by the palm oil industry. Yet instead of ensuring law and order, the Ecuadorian authorities are siding with the companies – the courts are working to break the resistance of the people by ordering them to pay damages for their protests.

Info: von Di. 29.7. bis Mo. 3. August ist wegen Renovierungsgedöns kein Versand möglich.
Bestellungen können wie immer im Shop vorgenommen werden, auch für Beratung bin ich da - doch ich kann in der Zeit weder anfertigen noch packen. Also Geschenke zeitig bestellen!

Cross-Timeslot Optimization for Distributed GPU Inference Using Reinforcement Learning
Chengze Du, Zhiwei Yu, Heng Xu, Haojie Wang, Bo liu, Jialong Li
https://arxiv.org/abs/2507.10259

Cross-Timeslot Optimization for Distributed GPU Inference Using Reinforcement Learning
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems rely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitati…

"Conspiracy thinking is also a trap because it contains feedback loops of positive reinforcement. If you reject authoritative sources of information as part of a conspiracy, then you will likely reject any information that can disprove the conspiracy. Any information that contradicts the conspiracy, or lack of information that would prove the conspiracy, are part of the conspiracy."

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
Luke Rowe, Rodrigue de Schaetzen, Roger Girgis, Christopher Pal, Liam Paull
https://arxiv.org/abs/2506.11234

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
We present Poutine, a 3B-parameter vision-language model (VLM) tailored for end-to-end autonomous driving in long-tail driving scenarios. Poutine is trained in two stages. To obtain strong base driving capabilities, we train Poutine-Base in a self-supervised vision-language-trajectory (VLT) next-token prediction fashion on 83 hours of CoVLA nominal driving and 11 hours of Waymo long-tail driving. Accompanying language annotations are auto-generated with a 72B-parameter VLM. Poutine is obtained …

CIRO7.2: A Material Network with Circularity of -7.2 and Reinforcement-Learning-Controlled Robotic Disassembler
Federico Zocco, Monica Malvezzi
https://arxiv.org/abs/2506.11748

CIRO7.2: A Material Network with Circularity of -7.2 and Reinforcement-Learning-Controlled Robotic Disassembler
The competition over natural reserves of minerals is expected to increase in part because of the linear-economy paradigm based on take-make-dispose. Simultaneously, the linear economy considers end-of-use products as waste rather than as a resource, which results in large volumes of waste whose management remains an unsolved problem. Since a transition to a circular economy can mitigate these open issues, in this paper we begin by enhancing the notion of circularity based on compartmental dynam…