Learning Agents
Learning Agents

강화학습 논문 리뷰 스터디 자료 저장소

2026 © Learning Agents

[논문 리뷰] Extreme Q-Learning: MaxEnt RL without Entropy

[논문 리뷰] Extreme Q-Learning: MaxEnt RL without Entropy

작성자: 김동민

2025, Mar 06    

논문 정보

제목: Extreme Q-Learning: MaxEnt RL without Entropy

저자: Divyansh Garg, Joey Hejna, Matthieu Geist, Stefano Ermon

학회: ICLR 2023

링크: https://arxiv.org/abs/2301.02328


발표 자료


# 김동민
« [논문 리뷰] Flow Q-Learning [논문 리뷰] Accelerating Reinforcement Learning with Learned Skill Priors »