Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo
This work provides an economic interpretation framework for AI systems, aiding researchers in understanding and explaining AI, though it is incremental in linking existing fields.
The paper clarifies connections between machine learning algorithms and econometric dynamic structural models by analyzing three game AIs, showing that Deep Blue, Bonanza, and AlphaGo correspond to specific econometric methods like calibrated value functions and conditional choice probability estimation.
Artificial intelligence (AI) has achieved superhuman performance in a growing number of tasks, but understanding and explaining AI remain challenging. This paper clarifies the connections between machine-learning algorithms to develop AIs and the econometrics of dynamic structural models through the case studies of three famous game AIs. Chess-playing Deep Blue is a calibrated value function, whereas shogi-playing Bonanza is an estimated value function via Rust's (1987) nested fixed-point method. AlphaGo's "supervised-learning policy network" is a deep neural network implementation of Hotz and Miller's (1993) conditional choice probability estimation; its "reinforcement-learning value network" is equivalent to Hotz, Miller, Sanders, and Smith's (1994) conditional choice simulation method. Relaxing these AIs' implicit econometric assumptions would improve their structural interpretability.