In Trust We Survive: Emergent Trust Learning
This work addresses cooperation challenges in multi-agent systems for applications like resource management and social dilemmas, though it appears incremental as it builds on existing trust-based methods.
The paper tackles the problem of enabling AI agents to cooperate in competitive game environments with shared resources by introducing Emergent Trust Learning (ETL), a lightweight trust-based control algorithm that reduces conflicts and prevents resource depletion while achieving competitive individual returns, as demonstrated in grid-based and hierarchical environments.
We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in competitive game environments under shared resources. Each agent maintains a compact internal trust state, which modulates memory, exploration, and action selection. ETL requires only individual rewards and local observations and incurs negligible computational and communication overhead. We evaluate ETL in three environments: In a grid-based resource world, trust-based agents reduce conflicts and prevent long-term resource depletion while achieving competitive individual returns. In a hierarchical Tower environment with strong social dilemmas and randomised floor assignments, ETL sustains high survival rates and recovers cooperation even after extended phases of enforced greed. In the Iterated Prisoner's Dilemma, the algorithm generalises to a strategic meta-game, maintaining cooperation with reciprocal opponents while avoiding long-term exploitation by defectors. Code will be released upon publication.