This paper presents an intelligent routing algorithm, called Q-Agents, which bases its actions only on the agent-environment interaction. This algorithm combines properties of three learning strategies (Q-learning, dual reinforcement learning and learning based on ant colony behavior), adding to them two further mechanisms to improve its adaptability. Hence, the proposed algorithm is composed of a set of agents, moving through the network independently and concurrently, searching for the best routes. The agents share knowledge about the quality of the paths traversed through indirect communication. Information about the network and traffic status is updated by using Q-learning and dual reinforcement updating rules. Q-Agents were applied to a model of an AT&T circuit-switched network. Experiments were carried out on the performance of the algorithm under variations of traffic patterns, load level and topology, and with addition of noise in the information used to route calls. Q-Agents suffered a lower number of lost calls than two algorithms based entirely on ant colony behavior.