Reinforcement learning in real-time communications

A method of training a reinforcement learning model for optimizing expected user-perceived quality of experience (QoE) in real-time communications, the method including

• determining, by a sending computing device, a current state of the sending computing device;
• determining a current action of the sending computing device;
• transmitting a real-time communication from the sending computing device to a receiving computing device, wherein the real-time communication includes one or more of a real-time audio communication and a real-time video communication;
• receiving a reward and network statistics of a network over which the first and second computing devices communicate, wherein the reward is based on one or more reception parameters associated with the real-time communication received at the receiving computing device;
• determining, based on the current state, the current action, the network statistics, and the reward, an expected value of a sum of a plurality of future rewards;
• and
• changing at least one of the plurality of transmission parameters to maximize the expected value of the sum of the plurality of future rewards.

A system to optimize expected user-perceived quality of experience (QoE) in real-time communications, comprising:

• a memory storing executable instructions;
• and
• a processor executing the executable instructions, which when executed, causes the processor to:
• determine, by the sending computing device, a current state of the sending computing device;
• determine a current action of the sending computing device;
• transmit, a real-time communication from the sending computing device to a receiving computing device, wherein the real-time communication includes one or more of a real-time audio communication and a real-time video communication;
• receive a reward and network statistics, wherein the reward is based on a parameter associated with the transmitted real-time communication received at the receiving computing device;
• determine, based on the current state, the network statistics, the current action, and the reward, an expected value of a sum of a plurality of future rewards;
• and
• change at least one of the plurality of transmission parameters of the sending computing device to maximize the expected value of the sum of the plurality of future rewards.