Intriguing! I have not yet read the paper, but it is obvious that the distinction between human and artificial actors is becoming more and more difficult.
From the abstract:
"But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification -- and modelling failures can lead to mistakes in the safety analysis. This paper proposes the first formal causal definition of agents -- roughly that agents are systems that would adapt their policy if their actions influenced the world in a different way. From this we derive the first causal discovery algorithm for discovering agents from empirical data, and give algorithms for translating between causal models and game-theoretic influence diagrams."
No comments:
Post a Comment