Abstract: Implementations are directed to converting a product representation stored in a computer-readable file to a mesh representation, the product representation including a multi-dimensional model of an object, generating a graph representation from the mesh representation, the graph representation including a set of vertices, each vertex associated with a set of coordinates in multi-dimensional space, providing a compound vector representation as a data structure including a set of vectors, each vector in the set of vectors including an m-bit vector that encodes a respective vertex of the set of vertices, the m-bit vector including a set of bit groups, each bit group representing a respective coordinate associated in the set of coordinates of the respective vertex, and processing the compound vector representation through a ML system to generate a prediction associated with the object.

Abstract: Implementations are directed to a set of intelligent assistants for execution with a computer-aided design (CAD) program, one or more intelligent assistants of the set of intelligent assistants processing a product representation of a product using one or more of embeddings and ML models to provide functionality to progress a design of the product through a design process.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reinforcement learning in agent training. Agents may be trained using reinforcement learning. The methods, systems, and apparatus include actions of obtaining scene grammars, obtaining a reference video of a reference agent performing a task, generating environments from the scene grammars, determining that behavior of a sample agent shown in a particular environment of the environments matches behavior of the reference agent, storing an indication that the particular environment trains agents to perform the task, determining to train a new agent to perform the task, identifying the particular environment based on the indication, and training the new agent to perform the task in the particular environments identified.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for agent environment co-creation. The methods, systems, and apparatus include actions of determining a success rate of an agent in an environment with a first complexity, determining that the success rate satisfies a complexity change criteria, in response to determining that the success rate satisfies the complexity change criteria, determining a second complexity that has a greater complexity than the first complexity, training the agent in the environment with the second complexity, and providing the agent trained in the environment with the second complexity.