Intrinsic fluctuations of reinforcement learning promote cooperation

TL;DR

This paper shows that intrinsic stochastic fluctuations in reinforcement learning processes significantly promote cooperation in social dilemmas, doubling cooperation rates and highlighting noise as a beneficial factor.

Contribution

It reveals that intrinsic noise in reinforcement learning, alongside other factors, critically enhances cooperation in multi-agent settings, a novel insight for designing cooperative algorithms.

Findings

Intrinsic fluctuations double cooperation rates to up to 80%.

Low exploration and small learning rates also promote cooperation.

Noise is a beneficial asset, not just a source of error.

Abstract

In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While evolutionary theory revealed a range of mechanisms promoting cooperation, the conditions under which agents learn to cooperate are contested. Here, we demonstrate which and how individual elements of the multi-agent learning setting lead to cooperation. We use the iterated Prisoner's dilemma with one-period memory as a testbed. Each of the two learning agents learns a strategy that conditions the following action choices on both agents' action choices of the last round. We find that next to a high caring for future rewards, a low exploration rate, and a small learning rate, it is primarily intrinsic stochastic fluctuations of the reinforcement learning process which double the final rate of cooperation to up to 80%. Thus, inherent noise is not a necessary evil of the iterative learning process. It is a critical asset for the learning of cooperation. However, we also point out the trade-off between a high likelihood of cooperative behavior and achieving this in a reasonable amount of time. Our findings are relevant for purposefully designing cooperative algorithms and regulating undesired collusive effects.