3 papers
cs.AI2026
Darwin Mobile Agent: A Roadmap for Self-Evolution
Daniel Beechey, Derek Yuen, Jianheng Liu +5
The goal of artificial intelligence is to create agents capable of general, adaptive behaviour in open-ended environments. Guided by the "Bitter Lesson", we argue that the most eff…
cs.LG2025
Approximating Shapley Explanations in Reinforcement Learning
Daniel Beechey, Ãzgür ÅimÅek
Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety…
cs.LG2025
A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values
Daniel Beechey, Thomas M. S. Smith, Ãzgür ÅimÅek
Reinforcement learning agents can achieve super-human performance in complex decision-making tasks, but their behaviour is often difficult to understand and explain. This lack of e…