Lars Buesing
Papers
1
Total Citations
2
H-Index
1
About
Lars Buesing is a leading researcher in artificial intelligence, with a primary focus on deep reinforcement learning (RL), neural network architectures, and the intersection of abstract reasoning with physical control. His work addresses a critical challenge in AI: enabling agents to solve tasks that require both high-level planning and low-level sensorimotor skills. Buesing’s most notable contribution is the introduction of a modular reinforcement learning approach for physically embodied agents, as demonstrated in his work on 3D Sokoban. This research moves beyond tabula-rasa methods by proposing architectures that decompose complex problems into manageable modules, allowing agents to integrate visual perception, abstract reasoning, and motor control. While his most-cited paper has garnered 2 citations, his broader influence is evident in the conceptual shift toward modular and hierarchical RL systems. Buesing’s work has been instrumental in advancing the field’s understanding of how to build agents that can operate in real-world environments, bridging the gap between simulated tasks and physical robotics. His research continues to inspire new directions in embodied AI and lifelong learning.
Research Focus
Key Achievements
Top Papers
- 1