This record contains the code and the experimental data of the bachelor's thesis "Dynamische Budget-Allokation in Multi-Objective Reinforcement Learning" (Dynamic Budget Allocation in Multi-Objective Reinforcement Learning) by Jonas Reichle, submitted at the University of Augsburg, Chair of Organic Computing, on 28 Sep...
Jonas Reichle, Neele Kemper, Jörg Hähner· Zenodo (CERN European Organi...· 0 citations
Neural network-based instance segmentation methods are essential for the automated diagnosis of patients with acne. However, a lack of pixel-wise annotations, which are time-consuming and labor-intensive to generate, severely impedes the development of segmentation algorithms for acne lesions. To tackle this issue, we...
This project investigates whether action-conditioned future latent prediction can improve visual representations learned by a vision-based navigation policy and their transfer to downstream reinforcement learning. The study uses the MetaDrive simulator to train and evaluate vision-based driving agents on procedurally g...
Shubham Waghmare· Zenodo (CERN European Organi...· 0 citations
Videos of trained reinforcement learning agents playing six Atari environments: Breakout, Mario Bros, Ms. Pac-Man, Pong, Space Invaders and Surround. Each environment includes 50 full episodes recorded as MP4 files. These videos complement the latent space analysis results published in a separate record. They show the...
Maxime Alaarabiou· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This record contains the code and the experimental data of the bachelor's thesis "Dynamische Budget-Allokation in Multi-Objective Reinforcement Learning" (Dynamic Budget Allocation in Multi-Objective Reinforcement Learning) by Jonas Reichle, submitted at the University of Augsburg, Chair of Organic Computing, on 28 Sep...
Jonas Reichle, Neele Kemper, Jörg Hähner· Zenodo (CERN European Organi...· 0 citations
We introduce the official open-access repository of the Amanollahi Geodesic Curvature Flow Solver, a breakthrough continuous optimization paradigm for Boolean Satisfiability (SAT) that definitively bridges a 40-year theoretical gap in pure continuous constraint satisfaction. Historically, continuous optimization framew...
Mohammadreza Sarvamanollahi· Zenodo (CERN European Organi...· 0 citations
Cloud-native microservice applications provide scalability and deployment flexibility but remain susceptible to service failures, cascading faults, and delayed recovery. This study presents a Self-Healing Microservice Architecture (SHMA) that combines Kubernetes-based container orchestration, autonomous AI agents, a bi...
Johnson Chidi Iheanachor· Asian Journal of Research in...· 0 citations
Abstract The increasing complexity of digital circuits has encouraged the use of Artificial Intelligence (AI) in Electronic Design Automation (EDA) to assist with logic synthesis, circuit optimization, and design analysis. Machine learning approaches, including Graph Neural Networks (GNNs) and Reinforcement Learning (R...
Christian Dave Tabarnilla· Zenodo (CERN European Organi...· 0 citations
Large language models increasingly emit confidence reports, predictive distributions, and typed decisions that determine whether a system answers, abstains, retrieves evidence, or spends more computation. We survey calibration-aware reinforcement learning (RL), in which a reported probability is scored by the reward, c...
Reinforcement learning (RL) has become a powerful and versatile paradigm in the era of large language models (LLMs). It is widely used to align models with human preferences and improve their reasoning capabilities. More recently, with the rapid rise of LLM-based agents, RL has become increasingly important for enablin...
Chenglong Wang, Hang Zhou, Tongran Liu et al.· Figshare· 0 citations
Online experiments are frequently employed in technological companies to evaluate the performance of a newly developed policy, product, or treatment relative to a baseline control. In many applications, the experimental units receive a sequence of treatments over time. To handle these time-dependent settings, existing...
Ke Sun, Linglong Kong, Hongtu Zhu et al.· Journal of the American Stat...· 0 citations
World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have advanced rapidly with the rise of foundation models and large-scale video generation....
Bohan Hou, Gen K. Li, Jindou Jia et al.· The International Journal of...· 0 citations
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026
