Efficient concept formation in large state spaces

General autonomous agents must be able to operate in previously unseen worlds with large state spaces. To operate successfully in such worlds, the agents must maintain their own models of the environment, based on concept sets that are several orders of magnitude smaller. For adaptive agents, those concept sets cannot be fixed, but must adapt continuously to new situations. This, in turn, requires mechanisms for forming and preserving those concepts that are critical to successful decision-making, while removing others. In this paper we compare four general algorithms for learning and decision-making: (i) standard Q-learning, (ii) deep Q-learning, (iii) single-agent local Q-learning, and (iv) single-agent local Q-learning with improved concept formation rules. In an experiment with a state space larger than 232, it was found that a single-agent local Q-learning agent with improved concept formation rules performed substantially better than a similar agent with less sophisticated concept formation rules and slightly better than a deep Q-learning agent