no code implementations • ICML 2020 • Kuno Kim, Megumi Sano, Julian De Freitas, Nick Haber, Daniel Yamins
World models are a family of predictive models that solve self-supervised problems on how the world evolves.
no code implementations • 15 Apr 2022 • Michael Poli, Winnie Xu, Stefano Massaroli, Chenlin Meng, Kuno Kim, Stefano Ermon
We investigate how to leverage the representations produced by Neural Collages in various tasks, including data compression and generation.
no code implementations • 28 Feb 2022 • Divyansh Garg, Skanda Vaidyanath, Kuno Kim, Jiaming Song, Stefano Ermon
Learning policies that effectively utilize language instructions in complex, multi-task environments is an important problem in sequential decision-making.
no code implementations • NeurIPS 2021 • Kuno Kim, Akshat Jindal, Yang song, Jiaming Song, Yanan Sui, Stefano Ermon
We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward.
no code implementations • 15 Jul 2020 • Kuno Kim, Megumi Sano, Julian De Freitas, Nick Haber, Daniel Yamins
Humans learn world models by curiously exploring their environment, in the process acquiring compact abstractions of high bandwidth sensory inputs, the ability to plan across long temporal horizons, and an understanding of the behavioral patterns of other agents.
1 code implementation • 9 Jul 2020 • Chuang Gan, Jeremy Schwartz, Seth Alter, Damian Mrowca, Martin Schrimpf, James Traer, Julian De Freitas, Jonas Kubilius, Abhishek Bhandwaldar, Nick Haber, Megumi Sano, Kuno Kim, Elias Wang, Michael Lingelbach, Aidan Curtis, Kevin Feigelis, Daniel M. Bear, Dan Gutfreund, David Cox, Antonio Torralba, James J. DiCarlo, Joshua B. Tenenbaum, Josh H. McDermott, Daniel L. K. Yamins
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal physical simulation.
1 code implementation • ICML 2020 • Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon
We formalize the Domain Adaptive Imitation Learning (DAIL) problem, which is a unified framework for imitation learning in the presence of viewpoint, embodiment, and dynamics mismatch.