Importing agent personalization instantiate a personalized agent in a user game session
Aspects of the present disclosure relate to a personalized agent service that generates and evolves customized agents that can be instantiated in-game to play with users. Machine learning models are trained to control the agent's interactions with the game environment and the user during gameplay. A user may request that a personalized agent join the user's gameplay session. The user device sends a request for the personalized agent to a game platform. The game platform determines whether the user has a license to execute a second instance of the game. When the user has a license to execute a second instance of the game, the second instance of the game may be executed on the user device. Information received from a personalized agent service is used to instantiate a personalized agent in the second instance of the game.
1. A system comprising:
at least one processor; and
memory encoding computer-executable instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receive, from a user device executing a first gameplay instance of a game, a request to instantiate a personalized agent in a personalized agent gameplay session of a second gameplay instance of the game, wherein the personalized agent using personalized agent data, and wherein the personalized agent data is generated based upon the operations comprising:
instantiating an agent in a gameplay session with a user for the second gameplay instance, wherein the instantiated agent is operable to interact with the user playing the game via the first gameplay instance based upon one or more machine learning models trained to play the game;
receiving, by the agent, a user interaction during gameplay;
generating, via the one or more machine learning models, an agent response to the user interaction;
instructing the agent to perform the agent response via the second gameplay instance;
receiving feedback to the agent response from the user; and
generating agent personalization data based upon the agent response and the user feedback;
determine, based upon the request, personalized agent data for an instantiated agent;
send the personalized agent data and to the user device;
establish a communication session with the user device;
receive game data from the user device corresponding to the first gameplay instance;
analyze the game data using the one or more machine learning models to determine one or more actions to be performed by the personalized agent; and
send the one or more actions to the user device.
2. The system of claim 1 , wherein the one or more machine learning models comprise:
a foundation model;
a language model;
a computer vision models; or
a speech model.
3. The system of claim 2 , wherein the video game data comprises one or more of:
visual data;
audio data;
haptic feedback data;
text data; or
data exposed through an API.
4. The system of claim 3 , wherein analyzing the game data comprises:
providing at least a portion of the video game data to a machine learning model trained to analyze the portion of the game data; and
based upon the output of the machine learning model, determining a current game state.
5. The system of claim 4 , wherein the one or more actions are determined based upon the current game state.
6. The system of claim 1 , wherein the request comprises parameter data related to at least one of:
an identifier for a specific personalized agent;
data related to one or more desired characteristics of the personalized agent;
game data; or
user data.
7. The system of claim 6 , wherein game data further comprises at least one of:
a game identifier;
information about a game genre; or
a server or world that a user character is playing on.
8. The system of claim 6 , wherein user data comprises at least one of:
data detailing characteristics of the user's character; or
data detailing the user's preferred play strategy.