Learning from Images in Offline Reinforcement Learning

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Machine Learning

Artificial Intelligence

Robotics

Learning from Images in Offline Reinforcement Learning

Offline Reinforcement Learning from Images with Latent Space Models

Offline reinforcement learning (rl) refers to the problem of learning policies from a static dataset of environment interactions.

Recent advances in model-based algorithms for offline rl have achieved state of the art results in state based tasks and have strong theoretical guarantees.

However, they rely crucially on the ability to quantify uncertainty in the model predictions, which is particularly challenging with image observations.

To overcome this challenge, we propose to learn a latent-state dynamics model, and represent the uncertainty in the latent space.

Our approach is both tractable in practice and corresponds to maximizing a lower bound of the lower bound of the equation for the exponentiation of the likelihood ratio in the unknown perturbation of the model predictions.

We also find that our approach excels on an image-based drawer closing task on a real robot using a pre-existing dataset.

Authors

Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn

◐ Latest Activity

◐ Recommended Follows