US 11,751,076 B2
Operation of sectorized communications from aerospace platforms using reinforcement learning
Sharath Ananth, Cupertino, CA (US); Brian Barritt, San Jose, CA (US); and Jin Zhang, Qingdao (CN)
Assigned to Aalyria Technologies, Inc., Livermore, CA (US)
Filed by Aalyria Technologies, Inc., Livermore, CA (US)
Filed on Jan. 12, 2023, as Appl. No. 18/153,806.
Application 18/153,806 is a continuation of application No. 17/520,188, filed on Nov. 5, 2021, granted, now 11,576,057.
Application 17/520,188 is a continuation of application No. 17/087,933, filed on Nov. 3, 2020, granted, now 11,202,214, issued on Dec. 14, 2021.
Application 17/087,933 is a continuation of application No. 16/593,536, filed on Oct. 4, 2019, granted, now 10,863,369, issued on Dec. 8, 2020.
Application 16/593,536 is a continuation of application No. 16/222,407, filed on Dec. 17, 2018, granted, now 10,477,418, issued on Nov. 12, 2019.
Prior Publication US 2023/0171617 A1, Jun. 1, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04B 7/185 (2006.01); H04W 24/00 (2009.01); H04W 4/00 (2018.01); G06N 3/02 (2006.01); H04W 24/02 (2009.01); G06N 3/08 (2023.01); H04W 84/06 (2009.01)
CPC H04W 24/02 (2013.01) [G06N 3/08 (2013.01); H04W 84/06 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of operating a communication network that includes a plurality of nodes, the method comprising:
receiving, by one or more processors, input data related to a state of the communication network and input data related to operation of the communication network for a first time interval;
determining, by the one or more processors, a first policy for the communication network based on the input data, the first policy being a set of features for forming a plurality of communication links in the communication network over the first time interval, the plurality of communication links providing one or more paths through the communication network;
determining, by the one or more processors, a performance metric associated with the first policy;
determining, by the one or more processors, a second policy for the communication network for a second time interval based at least in part on the performance metric associated with the first policy; and
operating, by the one or more processors, the communication network to implement the second policy in the second time interval.