KeyIn: Discovering Subgoal Structure with Keyframe-based Video Prediction

By Karl Pertsch, Oleh Rybkin, Jingyun Yang, Konstantinos G. Derpanis, Joseph J. Lim, Kostas Daniilidis, Andrew Jaegle. 2019

7 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Josh Tenenbaum
3. Peter W. Battaglia
4. Abhinav Kumar Gupta
5. Sergey Levine
6. Ruslan Salakhutdinov
7. Zhe Gan
8. Trevor Darrell

Citations in the corpus

• Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, neutral): “Among them, both [52] and [76] employ sequential variational models to infer either task boundaries or key frames of demonstrations in an unsupervised manner, followed by applications to hierarchical RL or planning.”
• CompILE: Compositional Imitation Learning and Execution (2018, background): “In concurrent work, Pertsch et al. (2019) introduced a differentiable model for keyframe discovery in sequence data, which is related to our setting.”
• The Tools Challenge: Rapid Trial-and-Error Learning in Physical Problem Solving (2019, background): “…event based model learning will be necessary to learn with such long horizons successfully (Jayaraman, Ebert, Efros, & Levine, 2018; Pertsch et al., 2019; Becker-Ehmck, Peters, & Van Der Smagt, 2019; Battaglia, Pascanu, Lai, Rezende, et al., 2016; Chang, Ullman, Torralba, &…”