Preprint
World models
Unknown
This paper introduces world models, enabling agents to learn and plan in latent spaces, leading to the Dreamer series for long-horizon reinforcement learning.
0Reinforcement Learning
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper introduces world models, enabling agents to learn and plan in latent spaces, leading to the Dreamer series for long-horizon reinforcement learning.
Danijar Hafner, J. Pašukonis, Jimmy Ba, et al.
Dreamer learns a world model from latent representations to enable planning and strong task performance across diverse domains.