Leveraging Demonstrations with Latent Space Priors

October 26, 2022 ยท Entered Twilight ยท ๐Ÿ› Trans. Mach. Learn. Res.

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CODE_OF_CONDUCT.md, CONTRIBUTING.md, LICENSE, README.md, config, cpp, format, hucc, requirements.txt, scripts, train.py, train_dist.py, train_zprior.py

Authors Jonas Gehring, Deepak Gopinath, Jungdam Won, Andreas Krause, Gabriel Synnaeve, Nicolas Usunier arXiv ID 2210.14685 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.RO Citations 9 Venue Trans. Mach. Learn. Res. Repository https://github.com/facebookresearch/latent-space-priors โญ 41 Last Checked 5 months ago
Abstract
Demonstrations provide insight into relevant state or action space regions, bearing great potential to boost the efficiency and practicality of reinforcement learning agents. In this work, we propose to leverage demonstration datasets by combining skill learning and sequence modeling. Starting with a learned joint latent space, we separately train a generative model of demonstration sequences and an accompanying low-level policy. The sequence model forms a latent space prior over plausible demonstration behaviors to accelerate learning of high-level policies. We show how to acquire such priors from state-only motion capture demonstrations and explore several methods for integrating them into policy learning on transfer tasks. Our experimental results confirm that latent space priors provide significant gains in learning speed and final performance. We benchmark our approach on a set of challenging sparse-reward environments with a complex, simulated humanoid, and on offline RL benchmarks for navigation and object manipulation. Videos, source code and pre-trained models are available at the corresponding project website at https://facebookresearch.github.io/latent-space-priors .
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning