ICLR 2021poster47 citations
Planning from Pixels using Inverse Dynamics Models
Keiran Paster, Sheila A. McIlraith, Jimmy Ba
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.
model based reinforcement learningdeep reinforcement learningmulti-task learningdeep learninggoal-conditioned reinforcement learning
BibTeX
@inproceedings{
paster2021planning,
title={Planning from Pixels using Inverse Dynamics Models},
author={Keiran Paster and Sheila A. McIlraith and Jimmy Ba},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=V6BjBgku7Ro}
}