25 citations · 58 across the 23 of their papers we have counts for
23 papers
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Junseok Kim, Dohyeong Kim, Mineui Hong +1
Compositional generalization is essential for reaching unseen goals under novel contextual variations in offline goal-conditioned reinforcement learning (GCRL), where a generalist…
Offline Reinforcement Learning with Universal Horizon Models
Hojun Chung, Junseo Lee, Songhwai Oh
Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from com…
RVN-Bench: A Benchmark for Reactive Visual Navigation
Jaewon Lee, Jaeseok Heo, Gunmin Lee +3
Safe visual navigation is critical for indoor mobile robots operating in cluttered environments. Existing benchmarks, however, often neglect collisions or are designed for outdoor…
Modality-Augmented Fine-Tuning of Foundation Robot Policies for Cross-Embodiment Manipulation on GR1 and G1
Junsung Park, Hogun Kee, Songhwai Oh
This paper presents a modality-augmented fine-tuning framework designed to adapt foundation robot policies to diverse humanoid embodiments. We validate our approach across two dist…
Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
Hogun Kee, Wooseok Oh, Minjae Kang +2
In this paper, we present the tidiness score-guided Monte Carlo tree search (TSMCTS), a novel framework designed to address the tabletop tidying up problem using only an RGB-D came…
Adversarial Environment Design via Regret-Guided Diffusion Models
Hojun Chung, Junseo Lee, Minsoo Kim +2
Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently eme…
RNR-Nav: A Real-World Visual Navigation System Using Renderable Neural Radiance Maps
Minsoo Kim, Obin Kwon, Howoong Jun +1
We propose a novel visual localization and navigation framework for real-world environments directly integrating observed visual information into the bird-eye-view map. While the r…
Semantic Environment Atlas for Object-Goal Navigation
Nuri Kim, Jeongho Park, Mineui Hong +1
In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes s…
Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach
Dohyeong Kim, Hyeokjin Kwon, Junseok Kim +2
As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method…
Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
Hyeokjin Kwon, Gunmin Lee, Junseo Lee +1
In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these co…
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Dohyeong Kim, Taehyun Cho, Seungyub Han +3
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-base…
Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
Dohyeong Kim, Mineui Hong, Jeongho Park +1
In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propos…
Diffused Task-Agnostic Milestone Planner
Mineui Hong, Minjae Kang, Songhwai Oh
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 leverag…
TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning
Dohyeong Kim, Songhwai Oh
As safety is of paramount importance in robotics, reinforcement learning that reflects safety, called safe RL, has been studied extensively. In safe RL, we aim to find a policy whi…
Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk
Dohyeong Kim, Songhwai Oh
This paper aims to solve a safe reinforcement learning (RL) problem with risk measure-based constraints. As risk measures, such as conditional value at risk (CVaR), focus on the ta…
Renderable Neural Radiance Map for Visual Navigation
Obin Kwon, Jeongho Park, Songhwai Oh
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. T…
Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding
Minyoung Hwang, Jaeyeon Jeong, Minsoo Kim +2
The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algo…
Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
Dohyeong Kim, Kyungjae Lee, Songhwai Oh
In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintainin…
Topological Semantic Graph Memory for Image-Goal Navigation
Nuri Kim, Obin Kwon, Hwiyeon Yoo +3
A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodi…
Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations
Seunggyu Chang, Jungchan Cho, Songhwai Oh
We propose a dual-domain generative model to estimate a texture map from a single image for colorizing a 3D human model. When estimating a texture map, a single image is insufficie…
Semi-Supervised Imitation Learning with Mixed Qualities of Demonstrations for Autonomous Driving
Gunmin Lee, Wooseok Oh, Seungyoun Shin +5
In this paper, we consider the problem of autonomous driving using imitation learning in a semi-supervised manner. In particular, both labeled and unlabeled demonstrations are leve…
Visually Grounding Language Instruction for History-Dependent Manipulation
Hyemin Ahn, Obin Kwon, Kyoungdo Kim +5
This paper emphasizes the importance of a robot's ability to refer to its task history, especially when it executes a series of pick-and-place manipulations by following language i…
NestedNet: Learning Nested Sparse Structures in Deep Neural Networks
Eunwoo Kim, Chanho Ahn, Songhwai Oh
Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works fo…