Personalized data driven game training system
A video game console, a video game system, and a computer-implemented method are described. Generally, a video game and video game assistance are adapted to a player. For example, a narrative of the video game is personalized to an experience level of the player. Similarly, assistance in interacting with a particular context of the video game is also personalized. The personalization learns from historical interactions of players with the video game and, optionally, other video games. In an example, a deep learning neural network is implemented to generate knowledge from the historical interactions. The personalization is set according to the knowledge.
1. A computer-implemented method comprising:
determining, by a computer system, an experience level of a video game player in playing a video game, the video game player represented by a virtual player in the video game;
generating, by the computer system based on inputting data about the experience level to an artificial intelligence (AI) model, a video game agent that, upon execution, interacts with the virtual player as another virtual player of the video game, the AI model trained based on historical interactions of video game players with one or more video games and on experience levels of the video game players, the AI model setting a parameter of the video game agent, wherein the parameter controls, based on the experience level of the video game player, an interaction of the video game agent with the virtual player; and
causing, by the computer system, an execution of the video game agent in the video game such that the virtual player interacts with the video game agent in the video game.
2. The computer-implemented method of claim 1 , wherein a second virtual player is presented in the video game based on the execution of the video game agent.
3. The computer-implemented method of claim 1 , wherein the AI model comprises a neural network, wherein an input layer of the neural network is mapped to the historical interactions of the video game players, wherein an output layer of the neural network is mapped to potential actions available to the video game players in the video game, and wherein the video game agent is configured to perform a subset of the potential actions based on the neural network.
4. The computer-implemented method of claim 3 , further comprising:
detecting, by the computer system, an interaction of the video game player with a context of the video game;
generating, by the computer system, an action of the video game agent from the potential actions based on inputting information about the interaction and the context to the neural network; and
causing, by the computer system, the video game agent to perform the action in response to the interaction of the video game player.
5. The computer-implemented method of claim 3 , wherein the neural network is trained based on the historical interactions of the video game players, and wherein the historical interactions are associated with a genre of the video game.
6. The computer-implemented method of claim 3 , wherein the neural network is trained based on a training dataset, wherein the training dataset comprises features vectors associated with the video game players, and wherein a feature vector comprises interactions, the experience levels, contexts of the video game, and sequences of actions in the video game.
7. A computer system comprising:
a processor; and
a memory storing computer-readable instructions that, upon execution by the processor, configure the computer system to:
determine an experience level of a video game player in playing a video game, the video game player represented by a virtual player in the video game;
generate, based on inputting data about the experience level to an artificial intelligence (AI) model, a video game agent that, upon execution, interacts with the virtual player as another virtual player of the video game, the AI model trained based on historical interactions of video game players with one or more video games and on experience levels of the video game players, the AI model setting a parameter of the video game agent, wherein the parameter controls, based on the experience level of the video game player, an interaction of the video game agent with the virtual player; and
cause an execution of the video game agent in the video game such that the virtual player interacts with the video game agent in the video game.
8. The computer system of claim 7 , wherein the experience level of the video game player is input to the AI model, wherein the AI model is further trained based on historical game session data of the video game players, wherein the video game players have different experience levels.
9. The computer system of claim 8 , wherein the parameter comprises a second experience level of the video game agent, wherein the second experience level is the same as or higher than the experience level of the video game player.
10. The computer system of claim 7 , wherein the experience level and game session data of the video game player are input to the AI model, and wherein the parameter is generated for the video game agent on the experience level and the game session data.
11. The computer system of claim 10 , wherein the video game agent comprises code, that upon execution, presents a second virtual player that plays with the virtual player of the video game player in the video game.
12. The computer system of claim 11 , wherein an output of the AI model comprises a value for the parameter associated with an action to be performed by the second virtual player in the video game.
13. The computer system of claim 12 , wherein the output of the AI model further comprises a second parameter and a second value for the second parameter associated with a presentation of the second virtual player in the video game.
14. The computer system of claim 10 , wherein the video game agent comprises code, that upon execution, presents an online handle that coaches the video game player in playing the video game.
15. The computer system of claim 14 , wherein the game session data comprises a context that the virtual player is interacting with in the video game, and wherein the parameter is defined for the context, and wherein an output of the AI model comprises a value for the parameter.
16. A video game console comprising:
a processor; and
a memory storing computer-readable instructions that, upon execution by the processor, configure the video game console to:
present, in a video game, a virtual player for a video game player, the video game player associated with an experience level in playing the video game;
access a video game agent that is generated based on inputting data about the experience level to an artificial intelligence (AI) model and that, upon execution, interacts with the virtual player as another virtual player of the video game, the AI model trained based on historical interactions of video game players with one or more video games and on experience levels of the video game players, the AI model setting a parameter of the video game agent, wherein the parameter controls, based on the experience level of the video game player, an interaction of the video game agent with the virtual player; and
execute the video game agent in the video game such that the virtual player interacts with the video game agent in the video game.
17. The video game console of claim 16 , wherein an output of the AI model comprises an action to be performed by the video game agent in the video game, and wherein the AI model is trained to select the action from potential actions based on a likelihood of success of an interaction with the virtual player upon a performance of the action by the video game agent.
18. The video game console of claim 17 , wherein the action is selected based on a predicted outcome of the action indicating that the AI model predicts a higher likelihood of success for the action relative to another action from the potential actions.
19. The video game console of claim 16 , wherein an input to the AI model comprises an interaction of the video game player with a context of the video game, the context, and the experience level of the video game player.
20. The video game console of claim 19 , wherein an output of the AI model comprises an action to be performed by the video game agent in the video game, and wherein the action is generated based on a feature vector associated with the interaction, the context, and the experience level.