Miroslav Pajic
2 papers · Latest:
Machine Learning
Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
This paper introduces an adaptive approach for policy selection and fine-tuning in offline-to-online reinforcement learning, optimizing online interaction budgets.
2605.05123
RoboticsSemantic Area Graph Reasoning for Multi-Robot Language-Guided Search
SAGR enables LLMs to coordinate multi-robot semantic search in unknown environments using a structured semantic-topological graph, improving efficiency.
2604.16263
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.