CPC H04W 72/121 (2013.01) [G06N 3/084 (2013.01); G06N 3/092 (2023.01); H04B 1/525 (2013.01); H04B 17/3913 (2015.01); H04W 16/22 (2013.01); H04W 24/02 (2013.01); H04W 28/0231 (2013.01); H04W 84/02 (2013.01); H04W 88/02 (2013.01); H04W 88/08 (2013.01); H04W 92/02 (2013.01); H04W 92/10 (2013.01); H04W 92/18 (2013.01)] | 15 Claims |
11. A method for selecting a plurality of terminal devices for uplink and downlink transmissions, comprising:
selecting a first terminal device from a first group of terminal devices; and
transferring the selected first terminal device from the first group of terminal devices to a second group of terminal devices;
wherein one group of terminal devices is scheduled for uplink transmission and the other group of terminal devices is scheduled for downlink transmission;
wherein the first terminal device is selected based at least on data rates of the terminal devices of the first group and data rates of the terminal devices of the second group using a reinforcement learning agent.
|