Invention Grant
- Patent Title: Action selection using interaction history graphs
-
Application No.: US16749252Application Date: 2020-01-22
-
Publication No.: US11636347B2Publication Date: 2023-04-25
- Inventor: Hanjun Dai , Yujia Li , Chenglong Wang , Rishabh Singh , Po-Sen Huang , Pushmeet Kohli
- Applicant: DeepMind Technologies Limited
- Applicant Address: GB London
- Assignee: DeepMind Technologies Limited
- Current Assignee: DeepMind Technologies Limited
- Current Assignee Address: GB London
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06K9/62 ; G06N3/04 ; G06N3/088 ; G06N3/049

Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.
Public/Granted literature
- US20200234145A1 ACTION SELECTION USING INTERACTION HISTORY GRAPHS Public/Granted day:2020-07-23
Information query