February 2026

I am taking a course on reinforcement learning and to pass the exam I need to propose and implement a project. After some thought, I came up with the idea of applying reinforcement learning to the problem of finding a sequence of actions, specifically, paper folds, that transform a flat sheet of paper into a desired target shape, given an origami model. It is a kind of inverse kinematics problem, but instead of robots, it is for sheets […]

Ver mais

This article covers how Azure ML’s persistent, workspace-centric compute resources differ from AWS SageMaker’s on-demand, job-specific approach. Additionally, we explored environment customization options, from Azure’s curated environments and custom environments to SageMaker’s three level of customizations. The post AWS vs. Azure: A Deep Dive into Model Training – Part 2 appeared first on Towards Data Science.

Ver mais

Autonomous mission planning for Active Debris Removal (ADR) must balance efficiency, adaptability, and strict feasibility constraints on fuel and mission duration. This work compares three planners for the constrained multi-debris rendezvous problem in Low Earth Orbit: a nominal Masked Proximal Policy Optimization (PPO) policy trained under fixed mission parameters, a domain-randomized Masked PPO policy trained across varying mission constraints for improved robustness, and a plain Monte Carlo Tree Search (MCTS) baseline. Evaluations are conducted in a high-fidelity orbital […]

Ver mais

For years, discovering YouTube creators from other parts of the world came with a familiar trade-off. You either accepted awkward subtitles or skipped the video altogether. Language has always been the barrier that decides what content travels and what stays local. YouTube has been trying to remove those barriers for a while now. To give you an example, YouTube started with basic captions, then came auto-translation, and eventually AI-powered voice dubbing. Today, the video streaming giant has announced […]

Ver mais

Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to alter the dynamics of their released simulators for malicious purposes. Therefore, in this work we highlight a novel threat, demonstrating how simulator dynamics can be exploited to stealthily implant action-level backdoors into RL agents. The backdoor then allows […]

Ver mais

Systematic literature reviews (SLRs) are fundamental to evidence-based research, but manual screening is an increasing bottleneck as scientific output grows. Screening features low prevalence of relevant studies and scarce, costly expert decisions. Traditional active learning (AL) systems help, yet typically rely on fixed query strategies for selecting the next unlabeled documents. These static strategies do not adapt over time and ignore the relational structure of scientific literature networks. This thesis introduces AutoDiscover, a framework that reframes AL as […]

Ver mais

The problem with existing camera-based Deep Reinforcement Learning approaches is twofold: they rarely integrate high-level scene context into the feature representation, and they rely on rigid, fixed reward functions. To address these challenges, this paper proposes a novel pipeline that produces a neuro-symbolic feature representation that encompasses semantic, spatial, and shape information, as well as spatially boosted features of dynamic entities in the scene, with an emphasis on safety-critical road users. It also proposes a Soft First-Order Logic […]

Ver mais