Slide 1
Slide 1 text
Survey on VLM and Reinforcement Learning in
Game Tasks (Minecraft)
STEVE-1: A Generative Model for Text-to-Behavior in
Minecraft,
Shalev Lifshitz et al. (University of Toronto et al.) [NeurIPS'23] (Cited by:28)
Auto MC-Reward: Automated Dense Reward Design with
Large Language Models for Minecraft,
Hao Li et al. (The Chinese University of Hong Kong et al.) [CVPR'24] (Cited by:5)
1/22
2024/07/10
MP5: A Multi-modal Open-ended Embodied System in
Minecraft via Active Perception,
Yiran Qin et al. (The Chinese University of Hong Kong et al.) [CVPR'24] (Cited
by:5)