Reinforcement learning in robotic process automation
AssigneeUiPath, Inc.
InventorsPrabhdeep Singh, Marco Alban Hidalgo
Life of this patent
Estimating the term…
Abstract
Reinforcement learning may be used to train machine learning (ML) models for robotic process automation (RPA) that are implemented by robots. A policy network may be employed, which learns to achieve a definite output by providing a particular input. In other words, the policy network informs the system whether it is getting closer to the winning state. The policy network may be refined by the robots automatically or with the periodic assistance of a human in order to reach the winning state, or to achieve a more optimal winning state. Robots may also create other robots that utilize reinforcement learning.
Claims16
A computer-implemented method for training a machine learning (ML) model for robotic process automation (RPA) using reinforcement learning, comprising:
- training the ML model by running simulations on training data using the ML model, the ML model having a reward function;
- and
- when the ML model does not achieve convergence defined by the reward function based on one or more criteria:
- requesting human assistance, monitoring actions taken by a human on a computing system, and modifying a policy network for the ML model, the reward function, or both, based on the actions taken by the human, wherein the trained ML model is configured to be called by an RPA robot;
- repeating the steps of running the simulations on the training data using the ML model, requesting human assistance, monitoring the actions taken by the human on the computing system, and modifying the policy network, the reward function, or both, until convergence is achieved.
A computer-implemented method for training a machine learning (ML) model for robotic process automation (RPA) using reinforcement learning, comprising:
- running simulations on training data using the ML model, the ML model having a reward function;
- when the ML model does not achieve convergence defined by the reward function based on one or more criteria:
- monitoring actions taken by a human on a computing system, and
- modifying a policy network for the ML model, the reward function, or both, based on the actions taken by the human;
- and
- repeating the steps of running the simulations on the training data using the ML model, monitoring the actions taken by the human on the computing system, and modifying the policy network, the reward function, or both, until convergence is achieved, wherein
- the trained ML model is configured to be called by an RPA robot.
Dependencies are inferred from the claim text.