WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

A generative model that learns to denoise data, achieving state-of-the-art image generation (Stable Diffusion, DALL-E 2).

Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.

In RL, the learner or decision-maker that takes actions in an environment to maximize cumulative reward.

In RL, the world the agent interacts with, providing states, accepting actions, and returning rewards.

A learned model of environment dynamics that can predict future states, used in model-based RL.

A collection of data examples used for training, validating, or testing machine learning models.

The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.

A non-linear function applied to neuron outputs that introduces non-linearity, enabling networks to learn complex patterns.

A function that turns a list of scores (logits) into probabilities that are all positive and sum to 1; the standard output of classifiers and language models.

Training a smaller 'student' model to mimic a larger 'teacher' model, transferring knowledge while reducing size.