Patent · US Active

Evaluating reinforcement learning policies

US10445653B1 · kind B1 · utility

6Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 7, 2015
Grant dateOct 15, 2019
Priority date
Expiry dateMay 20, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/022
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating reinforcement learning policies. One of the methods includes receiving a plurality of training histories for a reinforcement learning agent; determining a total reward for each training observation in the training histories; partitioning the training observations into a plurality of partitions; determining, for each partition and from the partitioned training observations, a probability that the reinforcement learning agent will receive the total reward for the partition if the reinforcement learning agent performs the action for the partition in response to receiving the current observation; determining, from the probabilities and for each total reward, a respective estimated value of performing each action in response to receiving the current observation; and selecting an action from the pre-determined set of actions from the estimated values in accordance with an action selection policy.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.