Social Reinforcement Learning for Changing Environments

If we imagine a dynamic environment whose behavior may change in time we can figure out the difficulties that agents located there will have trying to solve problems related to this environment. Changes in an environment e.g. a market, can be quite drastic: from changing the dependencies of some products to add new actions to build new products. The agents should try to cooperate or compete against others, when appropriated, to reach their goals faster than in an individual fashion, showing an always desirable emergent behavior. In this paper a reinforcement learning method proposal, guided by social interaction between agents, is presented. The proposal aims to show that adaptation is performed independently by the society where which these AI-controlled players belong, without explicitly reporting that changes have occurred by a central authority, or even by trying to recognize those changes.