research
∙
03/16/2023
A Picture is Worth a Thousand Words: Language Models Plan from Pixels
Planning is an important capability of artificial agents that perform lo...
share
research
∙
02/17/2023
Unsupervised Task Graph Generation from Instructional Video Transcripts
This work explores the problem of generating task graphs of real-world a...
research
∙
02/17/2023
Multimodal Subtask Graph Generation from Instructional Videos
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a d...
research
∙
05/25/2022
Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
We tackle real-world problems with complex structures beyond the pixel-b...
research
∙
03/28/2022
Learning Parameterized Task Structure for Generalization to Unseen Entities
Real world tasks are hierarchical and compositional. Tasks can be compos...
research
∙
11/18/2021
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Operating in the real-world often requires agents to learn about a compl...
research
∙
07/13/2021
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on ...
research
∙
10/28/2020
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments
First-person object-interaction tasks in high-fidelity, 3D, simulated en...
research
∙
02/08/2020
BRPO: Batch Residual Policy Optimization
In batch reinforcement learning (RL), one often constrains a learned pol...
research
∙
01/01/2020
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
We propose and address a novel few-shot RL problem, where a task is char...
research
∙
07/19/2018