This paper deals with Quality of Service-Routing (QoS-routing) in telecommunication networks with irregular traffics. The prediction of congestion’s problems in the networks in real time is quite difficult, making the effectiveness of ”traditional” methodologies based on analytical models questionable. An adaptive routing algorithm called Q-Neural Routing is proposed here. Compared to standard Q-Routing, the Q-value is approximated by a reinforcement learning based neural network of a fixed size, allowing the learner to incorporate various parameters such as local queue size and time of day, into its distance estimation. Moreover, each router uses an on line learning module to optimize the path in terms of average packet delivery time, by taking into account the waiting queue states of neighboring routers. The performance of the proposed algorithm is evaluated experimentally with OPNET simulator for different levels of load and compared to standard RIP and Q-Routing algorithms.