4 papers
Automatic Prompt Optimization for Dataset-Level Feature Discovery
Adrian Cosma, Oleg Szehr, David Kletz +2
Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed featu…
Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learning
Ardian Selmonaj, Miroslav Strupl, Oleg Szehr +1
To reliably deploy Multi-Agent Reinforcement Learning (MARL) systems, it is crucial to understand individual agent behaviors. While prior work typically evaluates overall team perf…
Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning
Ardian Selmonaj, Oleg Szehr, Giacomo Del Rio +3
This work presents a Hierarchical Multi-Agent Reinforcement Learning framework for analyzing simulated air combat scenarios involving heterogeneous agents. The objective is to iden…
On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers
Miroslav Štrupl, Oleg Szehr, Francesco Faccio +3
This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Tran…