/Patent Tracker
GooglePatent applicationAI & softwareInterest 4/10

Google patents method to teach AI agents using adjusted rewards

This filing describes a way to train artificial intelligence agents to perform tasks without needing a pre-built model of how the environment works. It uses a technique called regularized Nash dynamics, which modifies the rewards the agent receives during training to help it learn more stable and effective strategies.

Why it mattersThis is a technical improvement for training AI systems that could make them better at learning complex tasks from experience alone.

In the filing’s own words

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network that is used to control an agent. In particular, the policy neural network can be trained through model-free reinforcement learning with regularized Nash dynamics.

What exactly they claim (claim 1)

1. A method of training a policy neural network used to control an agent interacting with an environment to perform a task, the method comprising: initializing a regularized control policy for controlling the agent; and at each of a plurality of training phases, performing operations comprising: generating training data for the task, the training data comprising, for each of a plurality of steps during a trajectory of performing the task, a tuple comprising data identifying (i) an observation, (ii) an action performed in response to the observation in the tuple, and (iii) a reward for the task; generating, from the training data, modified training data for a modified task, comprising, for each tuple: generating a transformed reward from the reward in the tuple using the regularized control policy as of the training phase, and generating a modified tuple comprising data identifying (i) the observation identified the tuple, (ii) the action identified in the tuple and (iii) the transformed reward for the tuple; and training the policy neural network on the modified training data; and after training the policy neural network, updating the regularized control policy to be a policy that selects actions using the policy neural network.

Facts

Company
Google (DeepMind Technologies Limited)
Official title
MODEL-FREE REINFORCEMENT LEARNING WITH REGULARIZED NASH DYNAMICS
Publication number
US20260260121A1
Application number
18878470
Filed
Jun 27, 2023
Published
Sep 3, 2026
Inventors
3
Claims
22

Classified under

G06N 3/092 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.