Prati
Younggyo Seo
Younggyo Seo
Research Scientist, Dyson Robot Learning Lab
Potvrđena adresa e-pošte na kaist.ac.kr - Početna stranica
Naslov
Citirano
Citirano
Godina
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
S Lee, Y Seo, K Lee, P Abbeel, J Shin
Conference on Robot Learning, 1702-1712, 2022
1682022
Context-aware dynamics model for generalization in model-based reinforcement learning
K Lee, Y Seo, S Lee, H Lee, J Shin
International Conference on Machine Learning, 5757-5766, 2020
1332020
State entropy maximization with random encoders for efficient exploration
Y Seo, L Chen, J Shin, H Lee, P Abbeel, K Lee
International Conference on Machine Learning, 9443-9454, 2021
1262021
Masked world models for visual control
Y Seo, D Hafner, H Liu, F Liu, S James, K Lee, P Abbeel
Conference on Robot Learning, 1332-1344, 2023
1062023
Reinforcement Learning with Action-Free Pre-Training from Videos
Y Seo, K Lee, S James, P Abbeel
arXiv preprint arXiv:2203.13880, 2022
1002022
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning
J Park, Y Seo, J Shin, H Lee, P Abbeel, K Lee
arXiv preprint arXiv:2203.10050, 2022
772022
Learning What to Defer for Maximum Independent Sets
S Ahn, Y Seo, J Shin
International Conference on Machine Learning, 134-144, 2020
692020
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning
J Kim, Y Seo, J Shin
Advances in Neural Information Processing Systems 34, 2021
542021
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
Y Seo, K Lee, I Clavera Gilaberte, T Kurutach, J Shin, P Abbeel
Advances in Neural Information Processing Systems 33, 2020
402020
Multi-view masked world models for visual robotic manipulation
Y Seo, J Kim, S James, K Lee, J Shin, P Abbeel
International Conference on Machine Learning, 30613-30632, 2023
362023
Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning
J Park, Y Seo, C Liu, L Zhao, T Qin, J Shin, TY Liu
Advances in Neural Information Processing Systems 34, 2021
232021
HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator
Y Seo, K Lee, F Liu, S James, P Abbeel
2022 IEEE International Conference on Image Processing (ICIP), 3943-3947, 2022
172022
Language Reward Modulation for Pretraining Reinforcement Learning
A Adeniji, A Xie, C Sferrazza, Y Seo, S James, P Abbeel
arXiv preprint arXiv:2308.12270, 2023
162023
Imitating Graph-Based Planning with Goal-Conditioned Policies
J Kim, Y Seo, S Ahn, K Son, J Shin
The Eleventh International Conference on Learning Representations, 2023
102023
Accelerating reinforcement learning with value-conditional state entropy exploration
D Kim, J Shin, P Abbeel, Y Seo
Advances in Neural Information Processing Systems 36, 2024
82024
Guide Your Agent with Adaptive Multimodal Rewards
C Kim, Y Seo, H Liu, L Lee, J Shin, H Lee, K Lee
Advances in Neural Information Processing Systems 36, 2024
72024
Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning
V Vosylius, Y Seo, J Uruç, S James
arXiv preprint arXiv:2405.18196, 2024
62024
The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning
C Sferrazza, Y Seo, H Liu, Y Lee, P Abbeel
arXiv preprint arXiv:2311.00924, 2023
52023
Continuous Control with Coarse-to-fine Reinforcement Learning
Y Seo, J Uruç, S James
arXiv preprint arXiv:2407.07787, 2024
12024
Visual Representation Learning with Stochastic Frame Prediction
H Jang, D Kim, J Kim, J Shin, P Abbeel, Y Seo
Forty-first International Conference on Machine Learning, 2024
12024
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20