Подписаться
Seungchan Kim
Seungchan Kim
Carnegie Mellon University
Подтвержден адрес электронной почты в домене cs.cmu.edu - Главная страница
Название
Процитировано
Процитировано
Год
Toward general-purpose robots via foundation models: A survey and meta-analysis
Y Hu, Q Xie, V Jain, J Francis, J Patrikar, N Keetha, S Kim, Y Xie, T Zhang, ...
arXiv preprint arXiv:2312.08782, 2023
832023
Deepmellow: removing the need for a target network in deep q-learning
S Kim, K Asadi, M Littman, G Konidaris
International Joint Conference on Artificial Intelligence (IJCAI) 2019, 2019
772019
Combating the compounding-error problem with a multi-step model
K Asadi, D Misra, S Kim, ML Littman
arXiv preprint arXiv:1905.13320, 2019
652019
Airdet: Few-shot detection without fine-tuning for autonomous exploration
B Li, C Wang, P Reddy, S Kim, S Scherer
European Conference on Computer Vision (ECCV) 2022, 2022
322022
Unsupervised online learning for robotic interestingness with visual memory
C Wang, Y Qiu, W Wang, Y Hu, S Kim, S Scherer
IEEE Transactions on Robotics 38 (4), 2446-2461, 2021
182021
Multi-robot multi-room exploration with geometric cue extraction and circular decomposition
S Kim, M Corah, J Keller, G Best, S Scherer
IEEE Robotics and Automation Letters 9 (2), 1190-1197, 2023
8*2023
Removing the Target Network from Deep Q-Networks with the Mellowmax Operator
S Kim, K Asadi, ML Littman, GD Konidaris
International Conference on Autonomous Agents and Multiagent Systems (AAMAS …, 2019
82019
Adaptive Temperature Tuning for Mellowmax in Deep Reinforcement Learning
S Kim, G Konidaris
NeurIPS 2019 Deep Reinforcement Learning Workshop, 2019
42019
MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions
C Ho*, S Kim*, B Moon, A Parandekar, N Harutyunyan, C Wang, K Sycara, ...
arXiv preprint arXiv:2409.15590, 2024
32024
Robotic interestingness via human-informed few-shot object detection
S Kim, C Wang, B Li, S Scherer
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022, 2022
32022
PIPE Planner: Pathwise Information Gain with Map Predictions for Indoor Robot Exploration
S Baek*, B Moon*, S Kim*, M Cao, C Ho, S Scherer, J Jeon
arXiv preprint arXiv:2503.07504, 2025
2025
MapExRL: Human-Inspired Indoor Exploration with Predicted Environment Context and Reinforcement Learning
N Harutyunyan*, B Moon*, S Kim, C Ho, A Hung, S Scherer
arXiv preprint arXiv:2503.01548, 2025
2025
Using Computational Analysis of Behavior To Discover Developmental Change In Memory-Guided Attention Mechanisms In Childhood
D Amso, L Govindarajan, P Gupta, D Placido, H Baumgartner, A Lynn, ...
PsyArXiv, 2021
2021
Adaptive Tuning of Temperature in Mellowmax using Meta-Gradients
S Kim
Brown University, 2020
2020
[Replication] A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
A Bagaria, S Kim, A Mazzetto, R Rodriguez-Sanchez
NeurIPS 2019 Reproducibility Challenge, 2019
2019
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–15