Meta-Agent for Reinforcement Learning
AssigneeOfferFit, Inc.
InventorVictor Kostyuk
Life of this patent
Estimating the term…
Abstract
A computing machine receives a request for an action by a meta-agent at the computing machine. The computing machine selects, using the meta-agent, an agent for determining an action responsive to the request. The agent is selected from a plurality of reinforcement learning agents. The agent is selected based on values in a dataset associated with the request. At least a portion of the dataset has predefined value types. The meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types. The computing machine transmits, to the selected agent, the request for the action to cause the agent to compute the action.
Claims20
A method comprising:
- receiving a request for an action by a meta-agent;
- selecting, using the meta-agent, an agent for determining an action responsive to the request, the agent being selected from a plurality of reinforcement learning agents, wherein the agent is selected based on values in a dataset associated with the request, wherein at least a portion of the dataset has predefined value types, wherein the meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types;
- and
- transmitting, to the selected agent, the request for the action to cause the agent to compute the action.
A non-transitory machine-readable medium storing instructions which, when executed by one or more computing machines, cause the one or more computing machines to perform operations comprising:
- receiving a request for an action by a meta-agent;
- selecting, using the meta-agent, an agent for determining an action responsive to the request, the agent being selected from a plurality of reinforcement learning agents, wherein the agent is selected based on values in a dataset associated with the request, wherein at least a portion of the dataset has predefined value types, wherein the meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types;
- and
- transmitting, to the selected agent, the request for the action to cause the agent to compute the action.
A system comprising:
- processing circuitry;
- and
- a memory storing instructions which, when executed by the processing circuitry, cause the processing circuitry to perform operations comprising:
- receiving a request for an action by a meta-agent;
- selecting, using the meta-agent, an agent for determining an action responsive to the request, the agent being selected from a plurality of reinforcement learning agents, wherein the agent is selected based on values in a dataset associated with the request, wherein at least a portion of the dataset has predefined value types, wherein the meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types;
- and
- transmitting, to the selected agent, the request for the action to cause the agent to compute the action.
Dependencies are inferred from the claim text.