팔로우
Geon-Hyeong Kim
Geon-Hyeong Kim
LG AI Research
lgresearch.ai의 이메일 확인됨 - 홈페이지
제목
인용
인용
연도
Monte-Carlo tree search for constrained POMDPs
J Lee, GH Kim, P Poupart, KE Kim
Advances in Neural Information Processing Systems 31, 2018
692018
Demodice: Offline imitation learning with supplementary imperfect demonstrations
GH Kim, S Seo, J Lee, W Jeon, HJ Hwang, H Yang, KE Kim
International Conference on Learning Representations, 2021
672021
Variational interaction information maximization for cross-domain disentanglement
HJ Hwang, GH Kim, S Hong, KE Kim
Advances in Neural Information Processing Systems 33, 22479-22491, 2020
442020
Multi-view representation learning via total correlation objective
HJ Hwang, GH Kim, S Hong, KE Kim
Advances in Neural Information Processing Systems 34, 12194-12207, 2021
322021
Monte-carlo tree search in continuous action spaces with value gradients
J Lee, W Jeon, GH Kim, KE Kim
Proceedings of the AAAI conference on artificial intelligence 34 (04), 4561-4568, 2020
212020
Lobsdice: Offline learning from observation via stationary distribution correction estimation
GH Kim, J Lee, Y Jang, H Yang, KE Kim
Advances in Neural Information Processing Systems 35, 8252-8264, 2022
17*2022
Variational inference for sequential data with future likelihood estimates
GH Kim, Y Jang, H Yang, KE Kim
International Conference on Machine Learning, 5296-5305, 2020
42020
Prospector: Improving LLM agents with self-asking and trajectory ranking
B Kim, Y Jang, L Logeswaran, GH Kim, YJ Kim, H Lee, M Lee
22023
Trust region sequential variational inference
GH Kim, Y Jang, J Lee, W Jeon, H Yang, KE Kim
Asian conference on machine learning, 1033-1048, 2019
22019
Bayesian optimistic kullback–leibler exploration
K Lee, GH Kim, P Ortega, DD Lee, KE Kim
Machine Learning 108, 765-783, 2019
22019
SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
Y Jang, GH Kim, J Lee, S Sohn, B Kim, H Lee, M Lee
Advances in Neural Information Processing Systems 36, 2024
2024
DfPO: Degeneration-free Policy Optimization via Action Masking in Natural Language Action Spaces
Y Jang, GH Kim, B Kim, H Lee, M Lee
2023
Information-theoretic state space model for multi-view reinforcement learning
HJ Hwang, S Seo, Y Jang, S Kim, GH Kim, S Hong, KE Kim
2023
Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration
Y Jang, GH Kim, B Kim, YJ Kim, H Lee, M Lee
Forty-first International Conference on Machine Learning, 0
현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요.
학술자료 1–14