Hannes Becker
Papers
1
Total Citations
8
H-Index
1
About
Hannes Becker is a rising figure in artificial intelligence and multi-agent systems, whose work focuses on the intersection of heuristic search and bounded suboptimal planning. His key research areas include graph-based discrete planning, learned heuristics, and scalable decision-making for multi-agent coordination. Becker’s most cited paper, "Bounded Suboptimal Search with Learned Heuristics for Multi-Agent Systems" (2019, 8 citations), addresses a critical challenge in AI: the exponential complexity of optimal search in large-scale problems. He demonstrates that while optimal algorithms become infeasible as problem complexity grows, integrating machine-learned heuristics can dramatically improve performance without sacrificing solution quality within bounded suboptimality guarantees. This contribution offers a practical bridge between theoretical optimality and real-world tractability, particularly for multi-agent planning tasks. Though early in his career, Becker’s work is already influencing researchers seeking efficient, scalable approaches to complex planning—a testament to the growing importance of learned heuristics in modern AI systems.
Research Focus
Key Achievements
Top Papers
- 1