One shot multi-user multiple-input multiple-output (mu-mimo) resource pairing using reinforcement learning based deep q network (dqn)

A method, comprising:

• encoding every sequence of multi-user multiple-input multiple-output (MU MIMO) beam combinations into a unique numerical value;
• adding a Q value into the encoded numerical value to produce a Q encoded value (Qencoded);
• providing each of the sequence of beam combinations with a unique designated bin;
• passing a matrix comprising a state representation through a deep Q network (DQN);
• and
• outputting, by the deep Q network (DQN), one or more optimal beams to assign to a user equipment (UE).

An apparatus, comprising:

• at least one processor;
• and
• at least one memory comprising computer program code,
• the at least one memory and computer program code configured, with the at least one processor, to cause the apparatus at least to
• encode every sequence of multi-user multiple-input multiple-output (MU MIMO) beam combinations into a unique numerical value;
• add a Q value into the encoded numerical value to produce a Q encoded value (Qencoded);
• provide each of the sequence of beam combinations with a unique designated bin;
• pass a matrix comprising a state representation for each of the beam combinations through a deep Q network (DQN);
• and
• output, by the deep Q network (DQN), one or more optimal beams to assign to a user equipment (UE).