no code implementations • 6 May 2023 • Bolin Lai, Fiona Ryan, Wenqi Jia, Miao Liu, James M. Rehg
Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality.
no code implementations • 30 Mar 2023 • Tyler Malloy, Miao Liu, Matthew D. Riemer, Tim Klinger, Gerald Tesauro, Chris R. Sims
This raises the question of how humans learn to efficiently represent visual information in a manner useful for learning tasks.
no code implementations • 6 Feb 2023 • Shuai Zhang, Meng Wang, Pin-Yu Chen, Sijia Liu, Songtao Lu, Miao Liu
Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs.
no code implementations • 16 Dec 2022 • Bolin Lai, Hongxin Zhang, Miao Liu, Aryan Pariani, Fiona Ryan, Wenqi Jia, Shirley Anugrah Hayati, James M. Rehg, Diyi Yang
We also explore the generalization ability of language models for persuasion modeling and the role of persuasion strategies in predicting social deduction game outcomes.
no code implementations • 28 Oct 2022 • Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob N. Foerster, Gerald Tesauro, Jonathan P. How
By directly comparing active equilibria to Nash equilibria in these examples, we find that active equilibria find more effective solutions than Nash equilibria, concluding that an active equilibrium is the desired solution for multiagent learning settings.
no code implementations • 23 Oct 2022 • Heshan Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.
no code implementations • 8 Aug 2022 • Bolin Lai, Miao Liu, Fiona Ryan, James M. Rehg
To this end, we design the transformer encoder to embed the global context as one additional visual token and further propose a novel Global-Local Correlation (GLC) module to explicitly model the correlation of the global token and each local token.
1 code implementation • 21 Mar 2022 • Wenqi Jia, Miao Liu, James M. Rehg
We introduce the novel problem of anticipating a time series of future hand masks from egocentric video.
1 code implementation • 7 Mar 2022 • Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob N. Foerster, Michael Everett, Chuangchuang Sun, Gerald Tesauro, Jonathan P. How
An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other agents and influence the evolution of future policies towards desirable behavior for its own benefit.
no code implementations • 1 Mar 2022 • JunKyu Lee, Michael Katz, Don Joven Agravante, Miao Liu, Geraud Nangue Tasse, Tim Klinger, Shirin Sohrabi
Our approach defines options in hierarchical reinforcement learning (HRL) from AIP operators by establishing a correspondence between the state transition model of AI planning problem and the abstract state transition system of a Markov Decision Process (MDP).
no code implementations • 8 Feb 2022 • Ronny Luss, Amit Dhurandhar, Miao Liu
Many works in explainable AI have focused on explaining black-box classification models.
3 code implementations • CVPR 2022 • Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei HUANG, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Ziwei Zhao, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Christian Fuegen, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
1 code implementation • 6 Oct 2021 • Jikun Kang, Miao Liu, Abhinav Gupta, Chris Pal, Xue Liu, Jie Fu
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL).
no code implementations • 29 Sep 2021 • Ronny Luss, Amit Dhurandhar, Miao Liu
Many works in explainable AI have focused on explaining black-box classification models.
1 code implementation • 20 Sep 2021 • Marwa Abdulhai, Dong-Ki Kim, Matthew Riemer, Miao Liu, Gerald Tesauro, Jonathan P. How
Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration.
no code implementations • 20 May 2021 • Miao Liu, Lingni Ma, Kiran Somasundaram, Yin Li, Kristen Grauman, James M. Rehg, Chao Li
Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space?
no code implementations • 26 Nov 2020 • Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James M. Rehg, Siyu Tang
We introduce a novel task of reconstructing a time series of second-person 3D human body meshes from monocular egocentric videos.
no code implementations • 23 Nov 2020 • Tyler Malloy, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro, Chris R. Sims
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm.
1 code implementation • 31 Oct 2020 • Dong-Ki Kim, Miao Liu, Matthew Riemer, Chuangchuang Sun, Marwa Abdulhai, Golnaz Habibi, Sebastian Lopez-Cot, Gerald Tesauro, Jonathan P. How
A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents.
no code implementations • 9 Oct 2020 • Tyler Malloy, Chris R. Sims, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro
We focus on the model-free reinforcement learning (RL) setting and formalize our approach in terms of an information-theoretic constraint on the complexity of learned policies.
no code implementations • 31 May 2020 • Yin Li, Miao Liu, James M. Rehg
Moving beyond the dataset, we propose a novel deep model for joint gaze estimation and action recognition in FPV.
1 code implementation • 28 Jan 2020 • Modjtaba Shokrian Zini, Mohammad Pedramfar, Matthew Riemer, Miao Liu
This work is aiming to discuss and close some of the gaps in the literature on models using options (and more generally coagents).
no code implementations • 31 Dec 2019 • Matthew Riemer, Ignacio Cases, Clemens Rosenbaum, Miao Liu, Gerald Tesauro
In this work we note that while this key assumption of the policy gradient theorems of option-critic holds in the tabular case, it is always violated in practice for the deep function approximation setting.
1 code implementation • ECCV 2020 • Miao Liu, Siyu Tang, Yin Li, James Rehg
Motivated by this, we adopt intentional hand movement as a future representation and propose a novel deep network that jointly models and predicts the egocentric hand motion, interaction hotspots and future action.
no code implementations • 25 Sep 2019 • Tyler James Malloy, Matthew Riemer, Miao Liu, Tim Klinger, Gerald Tesauro, Chris R. Sims
We formalize this type of bounded rationality in terms of an information-theoretic constraint on the complexity of policies that agents seek to learn.
no code implementations • 5 Apr 2019 • Miao Liu, Xin Chen, Yun Zhang, Yin Li, James M. Rehg
To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for recognition.
Ranked #36 on
Action Recognition
on UCF101
no code implementations • 7 Mar 2019 • Dong-Ki Kim, Miao Liu, Shayegan Omidshafiei, Sebastian Lopez-Cot, Matthew Riemer, Golnaz Habibi, Gerald Tesauro, Sami Mourad, Murray Campbell, Jonathan P. How
Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers.
1 code implementation • ICLR 2019 • Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro
In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples.
no code implementations • NeurIPS 2018 • Matthew Riemer, Miao Liu, Gerald Tesauro
Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning.
no code implementations • ECCV 2018 • Yin Li, Miao Liu, James M. Rehg
We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera.
no code implementations • 20 May 2018 • Shayegan Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro, Matthew Riemer, Christopher Amato, Murray Campbell, Jonathan P. How
The problem of teaching to improve agent learning has been investigated by prior works, but these approaches make assumptions that prevent application of teaching to general multiagent problems, or require domain expertise for problems they can apply to.
no code implementations • ICLR 2018 • Xiaoxiao Guo, Shiyu Chang, Mo Yu, Miao Liu, Gerald Tesauro
In this paper, we consider a realistic and more difficult sce- nario where a reinforcement learning agent only has access to the state sequences of an expert, while the expert actions are not available.
no code implementations • 11 Dec 2017 • Miao Liu, Marlos C. Machado, Gerald Tesauro, Murray Campbell
Eigenoptions (EOs) have been recently introduced as a promising idea for generating a diverse set of options through the graph Laplacian, having been shown to allow efficient exploration.
Efficient Exploration
Hierarchical Reinforcement Learning
+1
no code implementations • ICLR 2018 • Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo, Miao Liu, Gerald Tesauro, Murray Campbell
Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning.
no code implementations • 24 Jul 2017 • Miao Liu, Kavinayan Sivakumar, Shayegan Omidshafiei, Christopher Amato, Jonathan P. How
We implement two variants of multi-robot Search and Rescue (SAR) domains (with and without obstacles) on hardware to demonstrate the learned policies can effectively control a team of distributed robots to cooperate in a partially observable stochastic environment.
2 code implementations • 26 Mar 2017 • Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How
For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to model subtle human behaviors and navigation rules (e. g., passing on the right).
no code implementations • 26 Sep 2016 • Yu Fan Chen, Miao Liu, Michael Everett, Jonathan P. How
Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e. g. goal) is unobservable to the others.
Multiagent Systems
no code implementations • 1 May 2015 • Miao Liu, Christopher Amato, Xuejun Liao, Lawrence Carin, Jonathan P. How
Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs).
1 code implementation • NeurIPS 2013 • Trevor Campbell, Miao Liu, Brian Kulis, Jonathan P. How, Lawrence Carin
This paper presents a novel algorithm, based upon the dependent Dirichlet process mixture model (DDPMM), for clustering batch-sequential data containing an unknown number of evolving clusters.