no code implementations • 11 Mar 2024 • Jongwook Choi, TaeHoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi
This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos.
1 code implementation • 5 Feb 2024 • Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad H. Danesh, Cyril Roumégous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João G. M. Araújo, Guorui Quan, Daniel Tan, Timo Klein, Rujikorn Charakorn, Mark Towers, Yann Berthelot, Kinal Mehta, Dipam Chakraborty, Arjun KG, Valentin Charraut, Chang Ye, Zichen Liu, Lucas N. Alegre, Alexander Nikulin, Xiao Hu, Tianlin Liu, Jongwook Choi, Brent Yi
As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone.
no code implementations • 25 May 2022 • Sungryull Sohn, Hyunjae Woo, Jongwook Choi, lyubing qiang, Izzeddin Gur, Aleksandra Faust, Honglak Lee
Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in testing.
Hierarchical Reinforcement Learning Meta Reinforcement Learning +2
no code implementations • ICLR 2022 • Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim
To address this issue, we propose Lipschitz-constrained Skill Discovery (LSD), which encourages the agent to discover more diverse, dynamic, and far-reaching skills.
1 code implementation • NeurIPS 2021 • Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, Aleksandra Faust
We learn to generate environments composed of multiple pages or rooms, and train RL agents capable of completing wide-range of complex tasks in those environments.
1 code implementation • NeurIPS 2021 • Christopher Hoang, Sungryull Sohn, Jongwook Choi, Wilka Carvalho, Honglak Lee
SFL leverages the ability of successor features (SF) to capture transition dynamics, using it to drive exploration by estimating state-novelty and to enable high-level planning by abstracting the state-space as a non-parametric landmark-based graph.
1 code implementation • 13 Jul 2021 • Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Mehdi Fatemi, Honglak Lee
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs.
no code implementations • 2 Jun 2021 • Jongwook Choi, Archit Sharma, Honglak Lee, Sergey Levine, Shixiang Shane Gu
Learning to reach goal states and learning diverse skills through mutual information (MI) maximization have been proposed as principled frameworks for self-supervised reinforcement learning, allowing agents to acquire broadly applicable multitask policies with minimal reward engineering.
1 code implementation • ICLR 2020 • Sungryull Sohn, Hyunjae Woo, Jongwook Choi, Honglak Lee
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent.
no code implementations • 25 Sep 2019 • Yijie Guo, Jongwook Choi, Marcin Moczulski, Samy Bengio, Mohammad Norouzi, Honglak Lee
We propose a new method of learning a trajectory-conditioned policy to imitate diverse trajectories from the agent's own past experiences and show that such self-imitation helps avoid myopic behavior and increases the chance of finding a globally optimal solution for hard-exploration tasks, especially when there are misleading rewards.
no code implementations • NeurIPS 2020 • Yijie Guo, Jongwook Choi, Marcin Moczulski, Shengyu Feng, Samy Bengio, Mohammad Norouzi, Honglak Lee
Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow.
no code implementations • ICLR 2019 • Jongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee
This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning.
Ranked #8 on Atari Games on Atari 2600 Montezuma's Revenge
no code implementations • CVPR 2018 • Seunghoon Hong, Dingdong Yang, Jongwook Choi, Honglak Lee
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout.
no code implementations • CVPR 2017 • Youngjae Yu, Jongwook Choi, Yeonhwa Kim, Kyung Yoo, Sang-Hun Lee, Gunhee Kim
The attention mechanisms in deep neural networks are inspired by human's attention that sequentially focuses on the most relevant parts of the information over time to generate prediction output.
no code implementations • CVPR 2017 • Youngjae Yu, Hyungjin Ko, Jongwook Choi, Gunhee Kim
We propose a high-level concept word detector that can be integrated with any video-to-language models.
Ranked #37 on Video Retrieval on LSMDC