检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hong, Mineui Kang, Minjae Oh, Songhwai Department of Electrical and Computer Engineering and ASRI Seoul National University Korea Republic of

Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as long-term planning, vision-based control, and multi-task decision-making. To this end, we propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space and to have an agent to follow the milestones to accomplish a given task. The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control. Furthermore, our approach exploits generation flexibility of the diffusion model, which makes it possible to plan diverse trajectories for multi-task decision-making. We demonstrate the proposed method across offline reinforcement learning (RL) benchmarks and an visual manipulation environment. The results show that our approach outperforms offline RL methods in solving long-horizon, sparse-reward tasks and multi-task problems, while also achieving the state-of-the-art performance on the most challenging vision-based manipulation benchmark. © 2023, CC0.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Do counterfactually fair image classifiers satisfy group fairness? - a theoretical and empirical study 24

Do counterfactually fair image classifiers satisfy group fai...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Sangwon Jung Sumin Yu Sanghyuk Chun Taesup Moon Department of Electrical and Computer Engineering Seoul National University NAVER AI Lab Department of Electrical and Computer Engineering Seoul National University and ASRI/INMC/IPAI/AIIS Seoul National University

ISBN: (纸本)9798331314385

The notion of algorithmic fairness has been actively explored from various aspects of fairness, such as counterfactual fairness (CF) and group fairness (GF). However, the exact relationship between CF and GF remains to be unclear, especially in image classification tasks; the reason is because we often cannot collect counter-factual samples regarding a sensitive attribute, essential for evaluating CF, from the existing images (e.g., a photo of the same person but with different secondary sex characteristics). In this paper, we construct new image datasets for evaluating CF by using a high-quality image editing method and carefully labeling with human annotators. Our datasets, CelebA-CF and LFW-CF, build upon the popular image GF benchmarks; hence, we can evaluate CF and GF simultaneously. We empirically observe that CF does not imply GF in image classification, whereas previous studies on tabular datasets observed the opposite. We theoretically show that it could be due to the existence of a latent attribute G that is correlated with, but not caused by, the sensitive attribute (e.g., secondary sex characteristics are highly correlated with hair length). From this observation, we propose a simple baseline, Counterfactual Knowledge Distillation (CKD), to mitigate such correlation with the sensitive attributes. Extensive experimental results on CelebA-CF and LFW-CF demonstrate that CF-achieving models satisfy GF if we successfully reduce the reliance on G (e.g., using CKD).

关键词：

来源：评论

学校读者我要写书评

暂无评论

MILAB at PragTag-2023: Enhancing Cross-Domain Generalization through Data Augmentation with Reduced Uncertainty 10

MILAB at PragTag-2023: Enhancing Cross-Domain Generalization...

引用

10th Workshop on Argument Mining, ArgMining 2023

作者： Lee, Yoonsang Lee, Dongryeol Jung, Kyomin College of Liberal Studies Seoul National University Korea Republic of Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of ASRI Seoul National University Korea Republic of

ISBN: (纸本)9798891760509

This paper describes our submission to the PragTag task, which aims to categorize each sentence from peer reviews into one of the six distinct pragmatic tags. The task consists of three conditions: full, low, and zero, each distinguished by the number of training data and further categorized into five distinct domains. The main challenge of this task is the domain shift, which is exacerbated by nonuniform distribution and the limited availability of data across the six pragmatic tags and their respective domains. To address this issue, we predominantly employ two data augmentation techniques designed to mitigate data imbalance and scarcity: pseudo-labeling and synonym generation. We experimentally demonstrate the effectiveness of our approaches, achieving the first rank under the zero condition and the third in the full and low conditions. © 2023 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object Rearrangement Planning for Target Retrieval in a Confined Space with Lateral View

Object Rearrangement Planning for Target Retrieval in a Conf...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Minjae Kang Junseok Kim Hogun Kee Songhwai Oh Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

In this paper, we perform an object rearrangement task for target retrieval in an environment with a confined space and limited observation directions. The agent must create a collision-free path to bring out the target object by relocating the surrounding objects using the prehensile action, i.e., pick-and-place. Object rearrangement in a confined space is a non-monotone problem, and finding a valid plan within a reasonable time is challenging. We propose a novel algorithm that divides the target retrieval task, which requires a long sequence of actions, into sequential sub-problems and explores each solution through Monte Carlo tree search (MCTS). In the experiment, we verify that the proposed algorithm can find safe rearrangement plans with various objects efficiently compared to the existing planning methods. Furthermore, we show that the proposed method can be transferred to a real robot experiment without additional training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Randomized Ensemble Multi-Agent Q-Learning

Attention-Based Randomized Ensemble Multi-Agent Q-Learning

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Jeongho Park Obin Kwon Songhwai Oh Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

Cooperative multi-agent scenarios are prevalent in real-world applications. Optimal coordination of agents requires appropriate task allocation, considering each task's complexity and each agent's capability. This becomes challenging under decentralization and partial observability, as agents must self-allocate tasks using limited state information. We introduce a novel multi-agent environment in which effective sub-task assignment is crucial for high-scoring performance. In addition, we propose a new multi-agent reinforcement learning framework named as attention-based randomized ensemble multi-agent Q-learning, or AREQ for short. This approach integrates a unique network structure using a multi-head attention mechanism, efficiently extracting task-related information from observations. AREQ also incorporates a randomized ensemble method, enhancing sample efficiency. We explore the impact of this attention-based structure and the random ensemble method through an ablation study and show AREQ's superiority compared to existing MARL methods within our proposed environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SDF-Based Graph Convolutional Q-Networks for Rearrangement of Multiple Objects

SDF-Based Graph Convolutional Q-Networks for Rearrangement o...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hogun Kee Minjae Kang Dohyeong Kim Jaegoo Choy Songhwai Oh Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

In this paper, we propose a signed distance field (SDF)-based deep Q-learning framework for multi-object re-arrangement. Our method learns to rearrange objects with non-prehensile manipulation, e.g., pushing, in unstructured environments. To reliably estimate Q-values in various scenes, we train the Q-network using an SDF-based scene graph as the state-goal representation. To this end, we introduce SDFGCN, a scalable Q-network structure which can estimate Q-values from a set of SDF images satisfying permutation invariance by using graph convolutional networks. In contrast to grasping-based rearrangement methods that rely on the performance of grasp predictive models for perception and movement, our approach enables rearrangements on unseen objects, including hard-to-grasp objects. Moreover, our method does not require any expert demonstrations. We observe that SDFGCN is capable of unseen objects in challenging configurations, both in the simulation and the real world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CONFIDENCE-BASED FEATURE IMPUTATION FOR GRAPHS WITH PARTIALLY KNOWN FEATURES

arXiv

引用

arXiv 2023年

作者： Um, Daeho Park, Jiwoong Park, Seulki Choi, Jin Young Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

This paper investigates a missing feature imputation problem for graph learning tasks. Several methods have previously addressed learning tasks on graphs with missing features. However, in cases of high rates of missing features, they were unable to avoid significant performance degradation. To overcome this limitation, we introduce a novel concept of channel-wise confidence in a node feature, which is assigned to each imputed channel feature of a node for reflecting certainty of the imputation. We then design pseudo-confidence using the channel-wise shortest path distance between a missing-feature node and its nearest known-feature node to replace unavailable true confidence in an actual learning process. Based on the pseudo-confidence, we propose a novel feature imputation scheme that performs channel-wise inter-node diffusion and node-wise inter-channel propagation. The scheme can endure even at an exceedingly high missing rate (e.g., 99.5%) and it achieves state-of-the-art accuracy for both semi-supervised node classification and link prediction on various datasets containing a high rate of missing features. Codes are available at https://***/daehoum1/pcfi. © 2023, CC BY-NC-ND.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Renderable Neural Radiance Map for Visual Navigation

arXiv

引用

arXiv 2023年

作者： Kwon, Obin Park, Jeongho Oh, Songhwai Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

We propose a novel type of map for visual navigation, a renderable neural radiance map (RNR-Map), which is designed to contain the overall visual information of a 3D environment. The RNR-Map has a grid form and consists of latent codes at each pixel. These latent codes are embedded from image observations, and can be converted to the neural radiance field which enables image rendering given a camera pose. The recorded latent codes implicitly contain visual information about the environment, which makes the RNR-Map visually descriptive. This visual information in RNR-Map can be a useful guideline for visual localization and navigation. We develop localization and navigation frameworks that can effectively utilize the RNR-Map. We evaluate the proposed frameworks on camera tracking, visual localization, and image-goal navigation. Experimental results show that the RNR-Map-based localization framework can find the target location based on a single query image with fast speed and competitive accuracy compared to other baselines. Also, this localization framework is robust to environmental changes, and even finds the most visually similar places when a query image from a different environment is given. The proposed navigation framework outperforms the existing image-goal navigation methods in difficult scenarios, under odometry and actuation noises. The navigation framework shows 65.7% success rate in curved scenarios of the NRNS [23] dataset, which is an improvement of 18.6% over the current state-of-the-art. Project page: https://***/projects/RNR-Map/ © 2023, CC BY-NC-SA.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hyeokjin Kwon Gunmin Lee Junseo Lee Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul Korea Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework improves algorithm performance by 39% and reduces constraint violations by 88% on the real-world Jackal platform, highlighting its effectiveness. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

关键词： Navigation Imitation learning Focusing Reinforcement learning Autonomous agents Safety Reliability Optimization Intelligent robots Faces

来源：评论

学校读者我要写书评

暂无评论

Model Reference Gaussian Process Regression: Data-Driven Output Feedback Controller

Model Reference Gaussian Process Regression: Data-Driven Out...

引用

American Control Conference (ACC)

作者： Hyuntae Kim Hamin Chang Hyungbo Shim Department of Electrical and Computer Engineering ASRI Seoul National University Seoul Korea

Data-driven controls using Gaussian process regression have recently gained much attention. In such approaches, system identification by Gaussian process regression is mainly followed by model-based controller designs. However, the outcomes of Gaussian process regression are often too complicated to apply conventional control designs, which makes the numerical design such as model predictive control employed in many cases. To overcome the restriction, our idea is to perform Gaussian process regression to the inverse of the plant with the same input/output data for the conventional regression. With the inverse, one can design a model reference controller without resorting to numerical control methods. This paper considers single-input single-output (SISO) discrete-time nonlinear systems of minimum phase with relative degree one. It is highlighted that the model reference Gaussian process regression (MR-GPR) controller is designed directly from precollected input/output data without identification of the system itself.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：