Prediction and Control with Temporal Segment Models

Understand

We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions.

• Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past action, and planned future action trajectories, as well as a latent prior over action trajectories.
• Our approach is based on convolutional autoregressive models and variational autoencoders.
• It makes stable and accurate predictions over long horizons for complex, stochastic systems, effectively expressing uncertainty and modeling the effects of collisions, sensory noise, and action delays.