Search Results for author: Haonan Yu

Found 25 papers, 14 papers with code

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

1 code implementation20 Jan 2024 Haonan Yu, Wei Xu

Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation.

Decoder Object +1

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

1 code implementation2 Feb 2023 Haichao Zhang, We Xu, Haonan Yu

With this approach, the policy previously learned offline is fully retained during online learning, thus mitigating the potential issues such as destroying the useful behaviors of the offline policy in the initial stage of online learning while allowing the offline policy participate in the exploration naturally in an adaptive manner.

reinforcement-learning Reinforcement Learning (RL)

Do You Need the Entropy Reward (in Practice)?

2 code implementations28 Jan 2022 Haonan Yu, Haichao Zhang, Wei Xu

On the other hand, our large-scale empirical study shows that using entropy regularization alone in policy improvement, leads to comparable or even better performance and robustness than using it in both policy improvement and policy evaluation.

Towards Safe Reinforcement Learning with a Safety Editor Policy

1 code implementation28 Jan 2022 Haonan Yu, Wei Xu, Haichao Zhang

On 12 Safety Gym tasks and 2 safe racing tasks, SEditor obtains much a higher overall safety-weighted-utility (SWU) score than the baselines, and demonstrates outstanding utility performance with constraint violation rates as low as once per 2k time steps, even in obstacle-dense environments.

2k reinforcement-learning +2

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

1 code implementation ICLR 2022 Haichao Zhang, Wei Xu, Haonan Yu

GPM can therefore leverage its generated multi-step plans for temporally coordinated exploration towards high value regions, which is potentially more effective than a sequence of actions generated by perturbing each action at single step level, whose consistent movement decays exponentially with the number of exploration steps.

reinforcement-learning Reinforcement Learning (RL)

TAAC: Temporally Abstract Actor-Critic for Continuous Control

2 code implementations NeurIPS 2021 Haonan Yu, Wei Xu, Haichao Zhang

TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario.

Continuous Control

Hierarchical Reinforcement Learning By Discovering Intrinsic Options

1 code implementation ICLR 2021 Jesse Zhang, Haonan Yu, Wei Xu

We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve sparse-reward tasks.

Hierarchical Reinforcement Learning reinforcement-learning +1

Why Build an Assistant in Minecraft?

1 code implementation22 Jul 2019 Arthur Szlam, Jonathan Gray, Kavya Srinet, Yacine Jernite, Armand Joulin, Gabriel Synnaeve, Douwe Kiela, Haonan Yu, Zhuoyuan Chen, Siddharth Goyal, Demi Guo, Danielle Rothermel, C. Lawrence Zitnick, Jason Weston

In this document we describe a rationale for a research program aimed at building an open "assistant" in the game Minecraft, in order to make progress on the problems of natural language understanding and learning from dialogue.

Natural Language Understanding

CraftAssist: A Framework for Dialogue-enabled Interactive Agents

3 code implementations19 Jul 2019 Jonathan Gray, Kavya Srinet, Yacine Jernite, Haonan Yu, Zhuoyuan Chen, Demi Guo, Siddharth Goyal, C. Lawrence Zitnick, Arthur Szlam

This paper describes an implementation of a bot assistant in Minecraft, and the tools and platform allowing players to interact with the bot and to record those interactions.

EPNAS: Efficient Progressive Neural Architecture Search

no code implementations7 Jul 2019 Yanqi Zhou, Peng Wang, Sercan Arik, Haonan Yu, Syed Zawad, Feng Yan, Greg Diamos

In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based on REINFORCE~\cite{Williams. 1992. PG}.

Neural Architecture Search

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP

no code implementations ICLR 2020 Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos

The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping the optimization process (Frankle & Carbin, 2019).

Image Classification Reinforcement Learning (RL)

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

2 code implementations NeurIPS 2019 Ari S. Morcos, Haonan Yu, Michela Paganini, Yuandong Tian

Perhaps surprisingly, we found that, within the natural images domain, winning ticket initializations generalized across a variety of datasets, including Fashion MNIST, SVHN, CIFAR-10/100, ImageNet, and Places365, often achieving performance close to that of winning tickets generated on the same dataset.

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

1 code implementation22 May 2018 Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning.

reinforcement-learning Reinforcement Learning (RL) +2

Listen, Interact and Talk: Learning to Speak via Interaction

1 code implementation28 May 2017 Haichao Zhang, Haonan Yu, Wei Xu

One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language.

Sentence

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

no code implementations28 Mar 2017 Haonan Yu, Haichao Zhang, Wei Xu

We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.

Language Acquisition Navigate +1

Robot Language Learning, Generation, and Comprehension

no code implementations25 Aug 2015 Daniel Paul Barrett, Scott Alan Bronikowski, Haonan Yu, Jeffrey Mark Siskind

We present a unified framework which supports grounding natural-language semantics in robotic driving.

Sentence Directed Video Object Codetection

no code implementations5 Jun 2015 Haonan Yu, Jeffrey Mark Siskind

We tackle the problem of video object codetection by leveraging the weak semantic constraint implied by sentences that describe the video content.

Activity Recognition Object +1

A Faster Method for Tracking and Scoring Videos Corresponding to Sentences

no code implementations14 Nov 2014 Haonan Yu, Daniel P. Barrett, Jeffrey Mark Siskind

Prior work presented the sentence tracker, a method for scoring how well a sentence describes a video clip or alternatively how well a video clip depicts a sentence.

Retrieval Sentence +1

Discriminative Training: Learning to Describe Video with Sentences, from Video Described with Sentences

no code implementations21 Jun 2013 Haonan Yu, Jeffrey Mark Siskind

We present a method for learning word meanings from complex and realistic video clips by discriminatively training (DT) positive sentential labels against negative ones, and then use the trained word models to generate sentential descriptions for new video.

Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.