The fitness landscape of social norms in social dilemmas
For researchers in multi-agent reinforcement learning and evolutionary game theory, this work provides a more general theoretical framework for understanding how social norms can evolve in stochastic environments.
This paper extends the evolutionary game theory of social norms from matrix games to Markov games, mapping norms over signal and reward spaces and providing a general solution and analysis of replicator dynamics for norm emergence.
By specifying behaviour across multiple agents, social norms are a coordination approach to resolving social dilemmas. Decentralized and wide adoption can be achieved by norms whose prescription involves interpreting stochastic signals in the environment. Such signals must have enough correlation to orchestrate mutually beneficial coordination and enough disincentivizing uncertainty about the benefits of exploiting that coordination. Evolutionary game theory of matrix games has been used to describe how, by rational agents comparing and adopting norms, a norm can evolve to become dominant in a population. Morsky \& Akçay (2019) classify norms according to a set of rationality criteria. Joint player strategies that adopt norms that are consistent with optimal single-player strategies with respect to expected reward naturally satisfy a correlated, rather than Nash game theoretic equilibrium condition. Here, we present a version of this theory that clarifies the basic ingredients. We formulate it in the more general Markov game setting more commonly used in reinforcement learning theory. We illustrate the theory by mapping norms over the signal and reward space, while also giving a detailed exposition of the underlying mechanics of the approach. Finally, we give a general solution and analysis of replicator dynamics, which Morsky \& Akçay (2019) propose as a means by which these norms could emerge.