A dynamic environment whose behavior may change in time presents a challenge that agents located there will have to solve. Changes in an environ-ment 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 working in this en-vironment would have to be ready to embrace this changes to improve their per-formance which otherwise would be diminished. Also, they 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 pa-per a reinforcement learning method proposal, guided by social interaction between agents, is presented. The proposal aims to show that adaptation is performed inde-pendently by the society, without explicitly reporting that changes have occurred by a central authority, and even without trying to recognize those changes.
展开▼