2015
NeurIPS
NeurIPS 2015
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
Abstract
We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear. Our model is derived directly from an optimal control formulation in latent space, supports long-term prediction of image sequences and exhibits strong performance on a variety of complex control problems.
🌱
Topic Pioneer
- Model-Based RL
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Reinforcement Learning and Robotics
📈
Trend Setter
- Variational Autoencoders
🧭
Keyword Pioneer
- variational autoencoder
🐣
Hot Topic Early Bird
- dynamical system
Topics
Artificial Intelligence > Core AI > Planning
Machine Learning > Core Methods > Representation Learning
Deep Learning > Models > Variational Inference
Robotics > Capabilities > Perception
Artificial Intelligence > Core AI > Robotics
Deep Learning > Learning Types > Model-Based RL
Reinforcement Learning > Methods > Model-Based RL
Deep Learning > Models > Variational Autoencoders