Neural Modular Control for Embodied Question Answering

October 26, 2018 Β· Entered Twilight Β· πŸ› Conference on Robot Learning

πŸŒ… TWILIGHT: Old Age
Predates the code-sharing era β€” a pioneer of its time

"No code URL or promise found in abstract"
"Code repo scraped from project page (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, .gitmodules, CODE_OF_CONDUCT.md, CONTRIBUTING.md, House3D, LICENSE, README.md, data, requirements.txt, training, utils

Authors Abhishek Das, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra arXiv ID 1810.11181 Category cs.AI: Artificial Intelligence Cross-listed cs.CL, cs.CV, cs.LG Citations 142 Venue Conference on Robot Learning Repository https://github.com/facebookresearch/EmbodiedQA ⭐ 316 Last Checked 6 days ago
Abstract
We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be executed by specialized sub-policies. Our choice of subgoals is compositional and semantic, i.e. they can be sequentially combined in arbitrary orderings, and assume human-interpretable descriptions (e.g. 'exit room', 'find kitchen', 'find refrigerator', etc.). We use imitation learning to warm-start policies at each level of the hierarchy, dramatically increasing sample efficiency, followed by reinforcement learning. Independent reinforcement learning at each level of hierarchy enables sub-policies to adapt to consequences of their actions and recover from errors. Subsequent joint hierarchical training enables the master policy to adapt to the sub-policies. On the challenging EQA (Das et al., 2018) benchmark in House3D (Wu et al., 2018), requiring navigating diverse realistic indoor environments, our approach outperforms prior work by a significant margin, both in terms of navigation and question answering.
Community shame:
Not yet rated
Community Contributions

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

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence