Decoding fairness: a reinforcement learning perspective
arXiv:2412.16249 · doi:10.1103/vk6m-48zs
Abstract
Behavioral experiments on the ultimatum game (UG) reveal that we humans prefer fair acts, which contradicts the prediction made in orthodox Economics. Existing explanations, however, are mostly attributed to exogenous factors within the imitation learning framework. Here, we adopt the reinforcement learning paradigm, where individuals make their moves aiming to maximize their accumulated rewards. Specifically, we apply Q-learning to UG, where each player is assigned two Q-tables to guide decisions for the roles of proposer and responder. In a two-player scenario, fairness emerges prominently when both experiences and future rewards are appreciated. In particular, the probability of successful deals increases with higher offers, which aligns with observations in behavioral experiments. Our mechanism analysis reveals that the system undergoes two phases, eventually stabilizing into fair or rational strategies. These results are robust when the rotating role assignment is replaced by a random or fixed manner, or the scenario is extended to a latticed population. Our findings thus conclude that the endogenous factor is sufficient to explain the emergence of fairness, exogenous factors are not needed.
12 pages, 13 figures. Comments are appreciated
References in corpus (17)
- An Introduction to Deep Reinforcement Learning
- Evolutionary game theory: Temporal and spatial effects beyond replicator dynamics
- Social physics
- Mathematical foundations of moral preferences
- Defense mechanisms of empathetic players in the spatial ultimatum game
- Grand challenges in social physics: In pursuit of moral behavior
- The Ultimatum Game in Complex Networks
- The effect of the topology on the spatial ultimatum game
- Accuracy in strategy imitations promotes the evolution of fairness in the spatial ultimatum game
- Evolution of cooperation in the public goods game with Q-learning
- Evolution of cooperation facilitated by reinforcement learning with adaptive aspiration levels
- Artificial intelligence meets minority game: toward optimal resource allocation
- Emergence of Cooperation in Two-agent Repeated Games with Reinforcement Learning
- Development of swarm behavior in artificial learning agents that adapt to different foraging environments
- Decoding trust: A reinforcement learning perspective
- Probabilistic fair behaviors spark its boost in the Ultimatum Game: the strength of good Samaritans
- Pinning control of social fairness in the Ultimatum game