Planning from Pixels Using Inverse Dynamics Models
Abstract
Learning dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn models in a latent space by learning to predict sequences of future actions conditioned on task completion. These models track task-relevant environment dynamics over a distribution of tasks, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.
Cite
Text
Paster et al. "Planning from Pixels Using Inverse Dynamics Models." International Conference on Learning Representations, 2021.Markdown
[Paster et al. "Planning from Pixels Using Inverse Dynamics Models." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/paster2021iclr-planning/)BibTeX
@inproceedings{paster2021iclr-planning,
title = {{Planning from Pixels Using Inverse Dynamics Models}},
author = {Paster, Keiran and McIlraith, Sheila A. and Ba, Jimmy},
booktitle = {International Conference on Learning Representations},
year = {2021},
url = {https://mlanthology.org/iclr/2021/paster2021iclr-planning/}
}