Abstract: This specification describes a system for generating positions of map items such as buildings, for placement on a virtual map. The system comprises: at least one processor; and a non-transitory computer-readable medium including executable instructions that when executed by the at least one processor cause the at least one processor to perform at least the following operations: receiving an input at a generator neural network trained for generating map item positions; generating, with the generator neural network, a probability of placing a map item for each subregion of a plurality of subregions of the region of the virtual map; and generating position data of map items for placement on the virtual map using the probability for each subregion.

Abstract: A player profile management system collects player data from various systems and generates and manages player profiles. A snapshot pipeline of the player profile management system generates a snapshot player profile associated with a player. The player profile management system receives, after generating the snapshot player profile associated with the player, player data associated with the player. An update pipeline of the player profile management system generates, based on the snapshot player profile and the player data associated with the player, an update player profile associated with the player.

Abstract: An anti-cheat system may be accessed over a network and stored directly into volatile memory of a user computing system. In some embodiments, this anti-cheat system may scan, or access portions of, the volatile memory of the user computing system to detect whether cheat software or other unauthorized software that may interact with a game application is detected on the user computing system. The accessed portions of the volatile memory may be compared with one or more signatures that are associated with the execution of cheat software on a computing system. The anti-cheat system may be prevented from being stored within non-volatile memory, thereby preventing malicious users from modifying the anti-cheat system.

Abstract: A streaming system may improving online gaming experiences for streaming players and/or providing device independent input processing. The streaming system may receive, from a client device, a selection of a game to be played via a streaming system, determine network connection parameters based at least in part on the game, determine a current streaming quality of the network connection of the client device, and determine the current streaming quality does not meet the network connection parameters. Based on the determination that the current streaming quality does not meet the network connection parameters, the streaming system may cause a prompt to be displayed to a player associated with the client device regarding alternative content for the player to play or cause at least a portion of the gameplay of the game to be slowed based at least in part on the current streaming quality and the network connection parameters.

Abstract: A method, computer-readable storage medium, and device for generating a character model. The method comprises: receiving an input image of a reference subject; processing the input image to generate a normalized image; identifying a set of features present in the normalized image, wherein each feature in the set of features corresponds to a portion of a head or body of the reference subject; for each feature in the set of features, processing at least a portion of the normalized image including the feature by a neural network model corresponding to the feature to generate a parameter vector corresponding to the feature; and combining the parameter vectors output by respective neural network models corresponding to respective features in the set of features to generate a parameterized character model corresponding to reference subject in the input image.

Abstract: This specification describes a computer-implemented method of generating an intent-based model for use in selecting actions in a video game. The method comprises initializing a graph comprising a plurality of nodes. Each node of the plurality of nodes represents a state of an entity in the video game. The method further comprises adding one or more edges to the graph. Each edge of the one or more edges represents a transition from a first state to a second state. The method further comprises determining, for each node of the plurality of nodes, a distance to each other node, comprising performing a path-finding algorithm on the graph. The method further comprises determining one or more outcome nodes. Each outcome node represents an outcome state of the entity. The method further comprises scoring the one or more outcome nodes, comprising, for each outcome node, determining a score based on an outcome of the outcome node. The method further comprises scoring the plurality of nodes of the graph.

Abstract: Systems and methods are provided for enhanced pose generation based on generative modeling. An example method includes accessing an autoencoder trained based on poses of real-world persons, each pose being defined based on location information associated with joints, with the autoencoder being trained to map an input pose to a feature encoding associated with a latent feature space. Information identifying, at least, a first pose and a second pose associated with a character configured for inclusion in an in-game world is obtained via user input, with each of the poses being defined based on location information associated with the joints and with the joints being included on a skeleton associated with the character. Feature encodings associated with the first pose and the second pose are generated based on the autoencoder. Output poses are generated based on transition information associated with the first pose and the second pose.

Abstract: A online gaming system may provide for a videographer mode in online gaming. The online gaming system may initiate an instance of an online game for players playing the online game in a player mode, establish connections to respective game clients of the players and to a videographer client of a computing device of a videographer, the videographer being a user participating in the online game in a videographer mode differing from the player mode, the videographer mode including capturing gameplay at least one of the players. Then, the online game system may receive player input data from at least one of the players, update a game state of the instance based on the player input data, and output respective game client data to the respective game clients and videographer client data the videographer client.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for preventing rendering of a character in a video game. The method includes receiving an action regarding a first character rendered in a first-person point of view (POV), the action causing the POV of the first character to change from the first-person POV to a third-person POV. The method includes detecting the POV of the first character is to be changed. The method includes determining characters are outside of a field of view (FOV) of the first character in the first-person POV and would be within the FOV of the first character in the third-person POV. The method includes changing the POV of the first character from the first-person POV to a third person POV. The method includes causing rendering of the video game in a third-person POV of the first character, the rendering preventing rendering of other characters.

Abstract: According to a first aspect of this specification, there is described a computer-implemented method of tagging video frames. The method comprises generating, using a frame tagging model, a tag for each of a plurality of frames of an animation sequence. The frame tagging model comprises: a first neural network portion configured to process, for each frame of the plurality of frames, a plurality of features associated with the frame and generate an encoded representation for the frame. The frame tagging model further comprises a second neural network portion configured to receive input comprising the encoded representations of each frame and generate output indicative of a tag for each of the plurality of frames.

Abstract: The present disclosure provides a system and method for updating a game application during runtime of a game application. The game application is executed on a client computing device using application code that includes a function store. During runtime of the game application, a function asset is received and stored in the function store. The function asset includes either precompiled code or code written in a scripting language and includes a version identifier. To execute a particular game function of the game application, the function asset is identified from other function assets in the function store based at least in part on its version identifier, and the game function is executed using the function asset.

Abstract: Embodiments of the systems and methods described herein provide a three dimensional reconstruction system that can receive an image from a camera, and then utilize machine learning algorithms to identify objects in the image. The three dimensional reconstruction system can identify a geolocation of a user, identify features of the surrounding area, such as structures or geographic features, and reconstruct the scene including the identified features. The three dimensional reconstruction system can generate three dimensional object data for the features and/or objects, modify the three dimensional objects, arrange the objects in a scene, and render a two dimensional view of the scene.

Abstract: Disclosed is a hybrid approach to rendering transparent or translucent objects, which combines object-space ray tracing with texture-space parametrization and integration. Transparent or translucent objects are first parameterized using two textures: (1) a texture that stores the surface normal at each location on the transparent or translucent object, and (2) a texture that stores the world space coordinates at each location on the transparent or translucent object. Ray tracing can then be used to streamline and unify the computation of light transport inside thick mediums, such as transparent or translucent objects, with the rest of the scene. For each valid (e.g., visible) location on the surface of a transparent or translucent object, the disclosed embodiments trace one or more rays through such objects and compute the resulting lighting in an order-independent fashion. The results are stored in a texture, which is then applied during the final lighting stage.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for changing music of a video game based on a player's emotion. The method includes receiving indicators of emotion comprising in-game attributes of a player in a video game. The method also includes predicting an emotion of the player based on the indicators of emotion from the video game. The method also includes receiving original music from the video game. The method also includes determining an original tone of the original music. The method also includes determining a transformed tone based at least in part on the emotion of the player that was predicted. The method also includes transforming the original tone of the original music to the transformed tone. The method also includes generating transformed music from the original music based on the transformed tone.

Abstract: This specification describes a computer-implemented method of generating speech audio for use in a video game, wherein the speech audio is generated using a voice convertor that has been trained to convert audio data for a source speaker into audio data for a target speaker. The method comprises receiving: (i) source speech audio, and (ii) a target speaker identifier. The source speech audio comprises speech content in the voice of a source speaker. Source acoustic features are determined for the source speech audio. A target speaker embedding associated with the target speaker identifier is generated as output of a speaker encoder of the voice convertor. The target speaker embedding and the source acoustic features are inputted into an acoustic feature encoder of the voice convertor. One or more acoustic feature encodings are generated as output of the acoustic feature encoder. The one or more acoustic feature encodings are derived from the target speaker embedding and the source acoustic features.

Abstract: Embodiments of the systems and methods disclosed herein provide a sponsor matching system in which players and sponsors can be matched. Upon a match based at least in part on stored sponsorship criteria and/or player preferences, a first sponsor can select a set of players to receive permission to select an advertisement associated with the first sponsor. Once a first player of the selected players selects an advertisement and an advertisement placement location associated with the first sponsor, the sponsor matching system can generate game rendering instructions for a first player system associated with the first player.

Abstract: A computer-implemented method comprises instantiating a policy function approximator. The policy function approximator is configured to calculate a plurality of estimated action probabilities in dependence on a given state of the environment. Each of the plurality of estimated action probabilities corresponds to a respective one of a plurality of discrete actions performable by the reinforcement learning agent within the environment. An initial plurality of estimated action probabilities in dependence on a first state of the environment are calculated. Two or more of the plurality of discrete actions are concurrently performed within the environment when the environment is in the first state. In response to the concurrent performance, a reward value is received. In response to the received reward value being greater than a baseline reward value, the policy function approximator is updated, such that it is configured to calculate an updated plurality of estimated action probabilities.

Abstract: A system and method for facilitating a user defined virtual space is disclosed. One or more virtual space locations and/or activities may be correlated with user specified geolocations. In some implementations, the user specified geolocations may be verified against one or more spatial requirements prior to recording the user selected space-geolocation correlations. A user request to initiate an action or activity in the virtual space may be received. Prior to executing the requested action or activity in the virtual space, the user current geolocation may be verified against that specified in a space-geolocation correlation corresponding to a virtual space location or activity indicated in the user request.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for learning a foreign language. The method includes executing a video game in a first human language. The method includes pausing gameplay of the video game for a paused time instance. The method includes executing a digital mini-puzzle game during the paused time instance in the gameplay of the video game, the digital mini-puzzle game executed in a second human language, the digital mini-puzzle game executed utilizing assets of the video game. The method includes receiving a response to the digital mini-puzzle game from a player-computing device corresponding to a player, the response comprising at least one of the first human language and/or the second human language. The method includes determining a score of the response corresponding to the player based at least in part on a comparison of the response with translation pairs in a database.

Abstract: A visual-programming tool processes nodes of a graph corresponding to operations or functions in program code associated with a plurality of programs, (e.g., games), stored as graph of nodes with logical connections signifying inputs, outputs, and/or units of connected nodes. The visual-programming tool resolves valid types and/or units associated with respective connected nodes and can propagate valid types and/or units throughout the graph.