Agent learning speeds shape spatial patterns and welfare in public goods games
Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas
Multiagent SystemsComputer Science and Game TheoryMachine Learning
Summary
When individuals decide where to move based on learning, their movement patterns can form clusters or traveling bands around resources. The researchers studied how different learning speeds for cooperative and selfish agents affect these patterns and overall community well-being. They found that when cooperators learn very quickly and defectors slowly, welfare can suffer due to overcrowding. Charging agents a cost for creating crowding helps improve community welfare again. These findings show the impact of individual learning behavior on group dynamics and resource sharing.
What this means in practice
- •For urban planners: Design movement incentives in shared public spaces to reduce crowding and improve overall community benefits by accounting for how people learn and adapt their movements.
- •For wildlife conservationists: Model animal group movement patterns influenced by learning and resource competition to better manage habitats and prevent harmful overconcentration.
Tested on simulated data.
Authors
Yefei Zhang, Yuxuan Zhao
Abstract
Spatial public goods models show that prescribed movement toward richer locations can generate spatial patterns. We ask how such patterns emerge when agents learn where to move and how learning rates shape their consequences for collective welfare. Fixed populations of cooperators and defectors independently learn movement policies using tabular Q-learning and local observations. Cooperator learning generates clusters around resource peaks, while co-adaptation changes their strength and motion. At a fixed training budget, the largest welfare losses occur when cooperators learn at high rates and defectors at low rates. In part of this regime, learned policies also generate traveling bands supported by a shared directional preference. The conditions supporting travel change with further training, so these patterns reflect training history rather than an established asymptotic outcome. Across the tested learning-rate conditions with cooperator learning, mean collective welfare falls below random movement because increased crowding outweighs gains in resource benefit. Charging agents for the crowding they impose on others during learning recovers much of the welfare loss in the tested conditions. These results connect learning rates to the emergence and welfare costs of spatial organization driven by individual rewards.