Tootfinder

> Note that Excepted Benefit HRAs, which can reimburse medical care expenses other than excepted benefits, are different from an HRA that reimburses only excepted benefits. Employers can continue to offer HRAs that reimburse only excepted benefits, and those HRAs need not meet the requirements for Excepted Benefit HRAs
...ok

Fossil fuel industry's 'climate false solutions' reinforce its power, aggravate environmental injustice, study suggests https://phys.org/news/2025-12-fossil-fuel-industry-climate-false.html

Fossil fuel industry's 'climate false solutions' reinforce its power, aggravate environmental injustice, study suggests
Many so-called low-carbon projects promoted by major oil and gas companies—including hydrogen, biofuels, carbon capture and storage, and carbon offsetting—operate as false solutions that not only fail to effectively reduce emissions, but also prolong the lifespan of fossil fuel infrastructures, entrench environmental injustices, and reinforce the political and economic power of the very industry responsible for the climate crisis.

The Distribution Shift Problem in Transportation Networks using Reinforcement Learning and AI
Federico Taschin, Abderrahmane Lazaraq, Ozan K. Tonguz, Inci Ozgunes
https://arxiv.org/abs/2509.15291

The Distribution Shift Problem in Transportation Networks using Reinforcement Learning and AI
The use of Machine Learning (ML) and Artificial Intelligence (AI) in smart transportation networks has increased significantly in the last few years. Among these ML and AI approaches, Reinforcement Learning (RL) has been shown to be a very promising approach by several authors. However, a problem with using Reinforcement Learning in Traffic Signal Control is the reliability of the trained RL agents due to the dynamically changing distribution of the input data with respect to the distribution o…

Cowboys deliver best defensive effort of the season vs. the Commanders -- and reinforcements are on the way

https://www.cbssports.com/nfl/news/cowboys-injury-updates-…

heise | Flach und flott: Das neue iPad Pro M5 im Test
Apple hat das iPad Pro nach 17 Monaten renoviert und ihm mit als Erstes den neuen Apple-Chip M5, mehr RAM und Wi-Fi 7 spendiert. Lohnt der höhere Preis?
https://www.

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Kaiwen Zheng, Huayu Chen, Haotian Ye, Haoxiang Wang, Qinsheng Zhang, Kai Jiang, Hang Su, Stefano Ermon, Jun Zhu, Ming-Yu Liu
https://arxiv.org/abs/2509.16117

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Recent works discretize the reverse sampling process to enable GRPO-style training, yet they inherit fundamental drawbacks, including solver restrictions, forward-reverse inconsistency, and complicated integration with classifier-free guidance (CFG). We introduce Diffusion Negative-aware FineTuning (DiffusionNFT), a new o…

"Australian tropical rainforest trees switch in world first from carbon sink to emissions source"
#Australia #Trees #Climate

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
Yujie Zhu, Charles A. Hepburn, Matthew Thorpe, Giovanni Montana
https://arxiv.org/abs/2509.15981

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
In reinforcement learning with sparse rewards, demonstrations can accelerate learning, but determining when to imitate them remains challenging. We propose Smooth Policy Regularisation from Demonstrations (SPReD), a framework that addresses the fundamental question: when should an agent imitate a demonstration versus follow its own policy? SPReD uses ensemble methods to explicitly model Q-value distributions for both demonstration and policy actions, quantifying uncertainty for comparisons. We …

RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
Chao Yu, Yuanqing Wang, Zhen Guo, Hao Lin, Si Xu, Hongzhi Zang, Quanlu Zhang, Yongji Wu, Chunyang Zhu, Junhao Hu, Zixiao Huang, Mingjie Wei, Yuqing Xie, Ke Yang, Bo Dai, Zhexuan Xu, Xiangyuan Wang, Xu Fu, Zhihao Liu, Kang Chen, Weilin Liu, Gang Liu, Boxun Li, Jianlei Yang, Zhi Yang, Guohao Dai, Yu Wang

RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workflows often lead to low hardware utilization and slow training on existing systems. In this paper, we present RLinf, a high-performance RL training system based on our key observation that the major roadblock to efficient RL training lies in system flexibility. To maximize flexib…

Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
Isaiah J. King, Benjamin Bowman, H. Howie Huang
https://arxiv.org/abs/2509.16151 https://

Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
Deep reinforcement learning (RL) is emerging as a viable strategy for automated cyber defense (ACD). The traditional RL approach represents networks as a list of computers in various states of safety or threat. Unfortunately, these models are forced to overfit to specific network topologies, rendering them ineffective when faced with even small environmental perturbations. In this work, we frame ACD as a two-player context-based partially observable Markov decision problem with observations rep…