I intend to use Q-learning (or any other reinforcement learning variant) to control the congestion window size of TCP. I know of an OPenAI-GYM library for NS-3 that provides an interface between NS-3 and Keras to implement reinforcement learning algorithms.

Is there anything similar to that in OMNeT++ as well? If there is none, what is the best way to implement reinforcement-learning in OMNeT++?

Best, Shahrukh

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.