Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a simulation of an environment that is being interacted with by a plurality of agents over a plurality of time steps, wherein the simulation comprises a respective simulation state for each time step that specifies a respective state of each agent at the time step. In one aspect, a method comprises, for each time step: obtaining a current simulation state for the current time step; generating a plurality of candidate next simulation states for a next time step; determining, for each candidate next simulation state, a discriminative score characterizing a likelihood that the candidate next simulation state is a realistic simulation state; and selecting a candidate next simulation state as the simulation state for the next time step based on the discriminative scores for the candidate next simulation states.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a simulation of an environment that is being interacted with by a plurality of agents over a plurality of time steps, wherein the simulation comprises a respective simulation state for each time step that specifies a respective state of each agent at the time step. In one aspect, a method comprises, for each time step: obtaining a current simulation state for the current time step; generating a plurality of candidate next simulation states for a next time step; determining, for each candidate next simulation state, a discriminative score characterizing a likelihood that the candidate next simulation state is a realistic simulation state; and selecting a candidate next simulation state as the simulation state for the next time step based on the discriminative scores for the candidate next simulation states.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating simulated trajectories using parallel beam search.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction that characterizes an environment. The system obtains an input including data characterizing observed trajectories one or more agents and data characterizing one or more map features identified in a map of the environment. The system generates, from the input, an encoder input that comprises representations for each of a plurality of points in a top-down representation of the environment. The system processes the encoder input using a point cloud encoder neural network to generate a global feature map of the environment, and processes a prediction input including the global feature map using a predictor neural network to generate a prediction output characterizing the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting actions for an agent at a specific real-world location using historical data generated at the same real-world location. One of the methods includes determining a current geolocation of an agent within an environment; obtaining historical data for geolocations in a vicinity of the current geolocation of the agent from a database that maintains historical data for a plurality of geolocations within the environment, the historical data for each geolocation comprising observations generated at least in part from sensor readings of the geolocation captured by vehicles navigating through the environment; generating an embedding of the obtained historical data; and providing the embedding as an input to a policy decision-making system that selects actions to be performed by the agent.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a simulation of an environment that is being interacted with by a plurality of agents over a plurality of time steps, wherein the simulation comprises a respective simulation state for each time step that specifies a respective state of each agent at the time step. In one aspect, a method comprises, for each time step: obtaining a current simulation state for the current time step; generating a plurality of candidate next simulation states for a next time step; determining, for each candidate next simulation state, a discriminative score characterizing a likelihood that the candidate next simulation state is a realistic simulation state; and selecting a candidate next simulation state as the simulation state for the next time step based on the discriminative scores for the candidate next simulation states.