Identifying Latent Intentions via Inverse Reinforcement Learning in Repeated Linear Public Good Games

TL;DR

This paper introduces a novel hierarchical inverse reinforcement learning method to identify latent intentions in repeated public goods games, revealing a new behavioral type and explaining cooperation dynamics.

Contribution

It develops a hierarchical inverse Q-learning framework and clustering method to uncover latent intentions and behavioral types in public goods game data.

Findings

Identifies a new behavioral type called Switchers that frequently reverse intentions.

Recovers canonical behaviors like cooperation and free-riding.

Shows that recognizing intention volatility can sustain cooperation.

Abstract

Behavior in repeated public goods games continues to challenge standard theory: heterogeneous social preferences can explain first-round contributions, but not the substantial volatility observed across repeated interactions. Using 50,390 decisions from 2,938 participants, we introduce two methodological advances to address this gap. First, we cluster behavioral trajectories by their temporal shape using Dynamic Time Warping, yielding distinct and theoretically interpretable behavioral types. Second, we apply a hierarchical inverse Q-learning framework that models decisions as discrete switches between latent cooperative and defective intentions. This approach reveals a large (21.4%) and previously unmodeled behavioral type -- Switchers -- who frequently reverse intentions rather than commit to stable strategies. At the same time, the framework recovers canonical strategic behaviors such as persistent cooperation and free-riding. Substantively, recognizing intentional volatility helps sustain cooperation: brief defections by Switchers often reverse, so strategic patience can prevent unnecessary breakdowns.