Microsoft Technology Licensing, LLC

David Michael Bignell

Katja Hofmann

Sam Michael Devlin

Jay Nanavati

Andrew Philip Slowey

Anthony David Joseph Diggle

Janhavi Agrawal

Adrian Kieron O'Grady

An apparatus is described for training a behavior of an agent in a physical or digital environment. The apparatus comprises a memory storing the location of at least one reward token in the environment. The location has been specified by a user. At least one processor executes the agent in the environment according to a behavior policy. The processor is configured to observe values of variables comprising: an observation of the agent, an action of the agent and any reward resulting from the reward token. The processor is configured to update the behavior policy using reinforcement learning according to the observed values.

Training behavior of an agent

Growing community of inventors

Cambridge, United Kingdom

David Michael Bignell