Hey ! I’m trying to implement a very simple PPO algorithm with numpy but I’m struggling with 2 things : – It seems that the actor net is not learning and I don’t know why. – some values go to nan after some epochs. I tried to comment as well as I could to keep it simple. Thank you very much for taking the time to help me: the environnement : a little grid 2d : “”” GAME […]
arXiv:2602.12476v1 Announce Type: new Abstract: Artificial intelligence (AI) companions are increasingly promoted as solutions for loneliness, often overlooking how personal dispositions and life-stage conditions shape artificial intimacy. Because intimacy is a primary coping mechanism for loneliness that varies by attachment style and age, we examine how different types of users form intimate relationships with AI companions in response to loneliness. Drawing on a hermeneutic literature review and a survey of 277 active AI companion users, we develop and […]
arXiv:2604.01325v1 Announce Type: new Abstract: The fundamental problem of causal inference – that the counterfactual outcome for any individual is never observed – has shaped the entire methodology of the field. Every existing approach substitutes assumptions for missing data: ignorability, parallel trends, exclusion restrictions. None produces the counterfactual itself. This paper proposes the Digital Twin Counterfactual Framework (DTCF): rather than estimating the counterfactual statistically, we simulate it using a digital twin and subject the simulation to a hierarchical […]
Claude can code, but can it check binary executables? We already did our experiments with using NSA software to hack a classic Atari game. This time, we want to focus on a much more practical task — using AI agents for malware detection. We partnered with Michał “Redford” Kowalczyk,a reverse engineering expert from Dragon Sector, known for finding malicious code in Polish trains, to create a benchmark of finding backdoors in binary executables, without access to source code. […]
If you’ve spent more than five minutes driving an electric vehicle, chances are good you’re a convert. But most people haven’t driven an EV, and surveys show that many are scared to consider ditching internal combustion engines for something that plugs in because of concerns about battery reliability. It’s easy to see why—if you don’t follow the field that closely, you’ll have missed some serious technology advances over the last few years. Early EVs did indeed suffer from […]
Verita AI is building the “Gym” for LLM reasoning. We are moving beyond simple chat-based RLHF into complex, grounded RL environments where models must solve multi-step engineering and research problems to receive a reward. The Mission Design robust, un-hackable RL environments (Prompt + Judge + Tools) that challenge top-tier models (GPT-5.2, Claude opus 4.6). Think SWE-Bench, but for AI/ML research. What We’re Looking For Technical Fluency: Deep PyTorch/JAX knowledge and the ability to debug distributed training. Adversarial Thinking: […]
arXiv:2602.11722v1 Announce Type: new Abstract: Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraints. We propose a PAC-Bayesian framework for deriving generalization bounds for fairness, covering both stochastic and deterministic classifiers. For stochastic classifiers, we derive a fairness bound using standard PAC-Bayes techniques. Whereas for deterministic classifiers, as usual PAC-Bayes arguments do not apply directly, […]
arXiv:2602.21334v1 Announce Type: new Abstract: As satellites have proliferated, interest has increased in autonomous rendezvous, proximity operations, and docking (ARPOD). A fundamental challenge in these tasks is the uncertainties when operating in space, e.g., in measurements of satellites’ states, which can make future states difficult to predict. Another challenge is that satellites’ onboard processors are typically much slower than their terrestrial counterparts. Therefore, to address these challenges we propose to solve an ARPOD problem with feedback optimization, which […]
Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to continuous learning while dealing with concept drifts, temporal dependence, and avoiding forgetting. Moreover, in IoT, different edge devices build up a network. When learning models on those devices, connecting them could be useful in improving performance and reusing others’ knowledge. This work proposes Mutual Assisted Learning, a learning paradigm grounded on Vygotsky’s popular […]
The explosive measles outbreak in South Carolina has now reached 789 cases, breaking Texas’s outbreak record last year of 762 cases, which at the time was the largest outbreak in the US since measles was declared eliminated from the US in 2000. The country is at grave risk of losing its elimination status in the coming months due to continuous spread. With Texas’ outbreak last year—which spanned January to August and spread to additional states—the US saw the […]