US 12,111,884 B2
Optimal sequential decision making with changing action space
Tanay Anand, Bangalore (IN); Pinkesh Badjatiya, Madhya Pradesh (IN); Sriyash Poddar, Howrah (IN); Jayakumar Subramanian, Maharashtra (IN); Georgios Theocharous, San Jose, CA (US); and Balaji Krishnamurthy, Uttar Pradesh (IN)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Apr. 20, 2022, as Appl. No. 17/659,983.
Prior Publication US 2023/0342425 A1, Oct. 26, 2023
Int. Cl. G06F 18/2137 (2023.01); G06N 3/088 (2023.01)
CPC G06F 18/2137 (2023.01) [G06N 3/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of machine learning, comprising:
receiving, by a monitoring component, state information that describes a state of a decision making agent in an environment;
computing, using a policy neural network of the decision making agent, an action vector from an action embedding space based on the state information, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and
performing, by the decision making agent, an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.