Share This Author
Habitat 2.0: Training Home Assistants to Rearrange their Habitat
- Andrew Szot, Alexander Clegg, Dhruv Batra
- Computer ScienceNeural Information Processing Systems
- 28 June 2021
Habitat 2.0 is introduced, a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios, and large-scale engineering contributions allow us to systematically compare deep reinforcement learning at scale and classical sense-plan-act pipelines in long-horizon structured tasks.
Generalization to New Actions in Reinforcement Learning
- Ayush Jain, Andrew Szot, Joseph J. Lim
- Computer ScienceInternational Conference on Machine Learning
- 12 July 2020
This work proposes a two-stage framework where the agent first infers action representations from action information acquired separately from the task, and a policy flexible to varying action sets is then trained with generalization objectives.
Generalizable Imitation Learning from Observation via Inferring Goal Proximity
- Youngwoon Lee, Andrew Szot, Shao-Hua Sun, Joseph J. Lim
- Psychology, Computer ScienceNeural Information Processing Systems
This work proposes a simple yet effective imitation learning from observation method for a goal-directed task using a learned goal proximity function as a task progress estimator for better generalization to unseen states and goals.
Housekeep: Tidying Virtual Households using Commonsense Reasoning
- Yash Kant, Arun Ramachandran, Harsh Agrawal
- Computer ScienceEuropean Conference on Computer Vision
- 22 May 2022
A modular baseline approach for Housekeep is proposed that lever-ages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning and shows that the baseline agent generalizes to rearranging unseen objects in unknown environments.
Generalizing Reinforcement Learning to Unseen Actions
Retrospectives on the Embodied AI Workshop
This analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR, grouped into three themes: visual navigation, rearrangement, and embodied vision-and-language.