Sungryull Sohn | DeepAI

DeepAI AI Chat

Featured Co-authors

Honglak Lee
119 publications
Ofir Nachum
58 publications
Satinder Singh
55 publications
Craig Boutilier
55 publications
Aleksandra Faust
40 publications
Kimin Lee
39 publications
Yinlam Chow
31 publications
Junhyuk Oh
20 publications
Moontae Lee
20 publications
Harm van Seijen
15 publications
Lajanugen Logeswaran
14 publications

∙ 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...

0 Anthony Z. Liu, et al. ∙

∙ 02/17/2023

Unsupervised Task Graph Generation from Instructional Video Transcripts

This work explores the problem of generating task graphs of real-world a...

0 Lajanugen Logeswaran, et al. ∙

∙ 02/17/2023

Multimodal Subtask Graph Generation from Instructional Videos

Real-world tasks consist of multiple inter-dependent subtasks (e.g., a d...

0 Yunseok Jang, et al. ∙

∙ 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...

1 Sungryull Sohn, et al. ∙

∙ 03/28/2022

Learning Parameterized Task Structure for Generalization to Unseen Entities

Real world tasks are hierarchical and compositional. Tasks can be compos...

6 Anthony Z. Liu, et al. ∙

∙ 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...

8 Christopher Hoang, et al. ∙

∙ 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 ...

10 Sungryull Sohn, et al. ∙

∙ 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...

10 Wilka Carvalho, et al. ∙

∙ 02/08/2020

BRPO: Batch Residual Policy Optimization

In batch reinforcement learning (RL), one often constrains a learned pol...

11 Sungryull Sohn, et al. ∙

∙ 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...

15 Sungryull Sohn, et al. ∙

∙ 07/19/2018

Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

We introduce a new RL problem where the agent is required to execute a g...

0 Sungryull Sohn, et al. ∙