Self-optimizing behaviors can lead to outcomes where collective benefits are ultimately destroyed, a well-known phenomenon known as the ``tragedy of the commons". These scenarios are widely studied using game-theoretic approaches to analyze strategic agent decision-making. In this paper, we examine this phenomenon in a bi-level decision-making hierarchy, where low-level agents belong to multiple distinct populations, and high-level agents make decisions that impact the choices of the local populations they represent. We study strategic interactions in a context where the populations benefit from a common environmental resource that degrades with higher extractive efforts made by high-level agents. We characterize a unique symmetric Nash equilibrium in the high-level game, and investigate its consequences on the common resource. While the equilibrium resource level degrades as the number of populations grows large, there are instances where it does not become depleted. We identify such regions, as well as the regions where the resource does deplete.
Figures & tables
Fig. 1 : The shaded green region depicts the set of all policies (δSP0,δRT0) that are responsible, as defined as in Definition 1 .
Fig. 2 : The resource extraction game is a strategic-form game among M players who each represent one of the greedy populations. Player i∈G chooses extraction rate αi≥0 for its population, where higher rates degrade the resource.
System Parameters
δSP0,δRT0
Responsible policy in deplete state (see Figure 1 )
δTR1,δPS1
Responsible policy in replete state (fixed, both positive)
α,θ
Consumption, restoration rates of responsible population
Decision Variables
αi
Consumption rate of greedy population i=1,…,M
αˉ
Total consumption rate of greedy populations
TABLE I : Parameters and variables of the multi-population system
Fig. 3 : (a) Resource level RM∗ under the symmetric equilibrium (Theorem 4.1 ) over the responsible policy space for M=6 greedy populations, with parameters θ=1.0,α=0.40,δTR1=2.1,δPS1=2.0 . The red dashed line indicates the curve C(0;δSP0) . Figures (b), (c), and (d) show the resource levels RM∗ vs. the number of greedy populations M for selected parameter values (shown as dots in subplot (a)). In (b), δRT0=0.8 is above C(0;δSP0) , meaning that α∗=θ/M for all M≥1 , leading to a constant value for RM∗ . In (c), δRT0=0.2>0 is below C(0;δSP0) . RM∗ decreases initially then stabilizes at a positive constant (Proposition 5.1 ). In (d) δRT0=−1.0<0 . RM∗ monotonically decreases toward zero, indicating complete resource depletion.
The tragedy of the commons poses a multi-agent safety problem: reward-seeking agents can deplete a shared resource, and cooperation among its users does not itself specify how much must be preserved. We make preservation an explicit requirement by formulating a regenerative commons as a constrained Markov game or a constrained multi-agent MDP with a designer-specified depletion budget. We develop a nonstationary Lagrangian framework that constructs a policy sequence from solutions of unconstrained games or cooperative control problems. Extending earlier time-average constructions, we introduce average-epoch solution concepts for reset episodes with discounted rewards and terminal costs. We prove a reward-independent feasibility certificate, cooperative feasibility and approximate optimality against feasible policy mixtures, and an extension to unbiased sampled costs. For self-interested agents, a constrained Nash certificate quantifies the price-dispersion term introduced by deviations that redistribute budget across epochs. Under the stated assumptions on solver accuracy and multiplier updates, these results give constrained policy-sequence guarantees using solutions of unconstrained problems. Experiments with constrained IPPO and MAPPO in a Gordon-Schaefer fishery examine how depletion budgets shape stock retention, harvest rewards, and price adaptation.
Jose Tupayachi, Xueping Li, Soham Das
Oak Ridge National Laboratory Department of Industrial and Systems Engineering, University of Tennessee, Knoxville · Department of Industrial and Systems Engineering, University of Tennessee, Knoxville
A group of non-cooperating agents can succumb to the tragedy-of-the-commons if all of them seek to maximize the same resource channel to improve their viability. In nature, however, groups often avoid such collapses by differentiating into distinct roles that exploit different resource channels. It remains unclear how such coordination can emerge under continual individual-level selection alone. To address this, we introduce a computational model of multi-level selection, in which group-level selection shapes a common substrate and mutation operator shared by all group members undergoing individual-level selection. We also place this process in an embodied ecology where distinct resource channels are not segregated, but coupled through the same behavioral primitives. These channels are classified as a positive-sum intake channel and a zero-sum redistribution channel. We investigate whether such a setting can give rise to role differentiation under turnover driven by birth and death. We find that in a learned ecology, both channels remain occupied at the colony level, and the collapse into a single acquisition mode is avoided. Zero-sum channel usage increases over generations despite not being directly optimized by group-level selection. Channel occupancy also fluctuates over the lifetime of a boid. Ablation studies suggest that most baseline performance is carried by the inherited behavioral basis, while the learned variation process provides a smaller but systematic improvement prior to saturation. Together, the results suggest that multi-level selection can enable groups in a common-pool setting to circumvent tragedy-of-the-commons through differentiated use of coupled channels under continual turnover.
Siddharth Chaturvedi, Ahmed El-Gazzar, Marcel van Gerven
Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University
We extend the study of learning in games to dynamics that exhibit non-asymptotic stability. We do so through the notion of uniform stability, which is concerned with equilibria of individually utility-seeking dynamics. Perhaps surprisingly, it turns out to be closely connected to economic properties of collective rationality. Up to strategic equivalence, if a mixed equilibrium is uniformly stable, then it is weakly Pareto optimal; there is no way for all players to improve by jointly deviating from the equilibrium. This is a form of collective rationality that rules out the types of behaviors in the prisoner's dilemma or the tragedy of the commons. Moreover, we show that uniform stability determines the last-iterate convergence behavior for the family of incremental smoothed best-response dynamics, used to model individual and corporate behaviors in the markets. Unlike dynamics around strict equilibria, which can stabilize to socially-inefficient solutions, individually utility-seeking behaviors near mixed Nash equilibria lead to collective rationality.