Jaeuk Shin

2 papers · 2021–2024 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (11)

Conferences

JMLR (1) L4DC (1)

Top co-authors

Insoon Yang (2) Giho Kim (1) Jeongho Kim (1) Howon Lee (1) Joonho Han (1)

Keywords

model-based learning (1) optimal control (1) dynamic programming (1) value estimation (1) meta-reinforcement learning (1) sample-efficient learning (1) deep q-learning (1) task inference (1) continuous-time system (1) lipchitz continuous control (1)

Papers

On task-relevant loss functions in meta-reinforcement learning L4DC 2024

Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls JMLR 2021