DayDreamer: World Models for Physical Robot Learning
To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the physical world. As a consequence, many advances in robot learning rely on simulators. On the other hand, learning inside of simulators fails to capture the complexity of the real world, is prone to simulator inaccuracies, and the resulting behaviors do not adapt to changes in the world. The Dreamer algorithm has recently shown great promise for learning from small amounts of interaction by planning within a learned world model, outperforming pure reinforcement learning in video games. Learning a world model to predict the outcomes of potential actions enables planning in imagination, reducing the amount of trial and error needed in the real environment. However, it is unknown whether Dreamer can facilitate faster learning on physical robots. In this paper,
Abstract To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the physical world. As a consequence, many advances in robot learning rely on simulators. On the other hand, learning inside of simulators fails to capture the complexity of the real world, is prone to simulator inaccuracies, and the resulting behaviors do not adapt to changes in the world. The Dreamer algorithm has recently shown great promise for learning…
saved by
related reading
- Introducing Dreamer: Scalable Reinforcement Learning Using World Modelsresearch.google
- Dream to Control: Learning Behaviors by Latent Imaginationdanijar.com
- State of Robot Learning, December 2025vedder.io
- [2509.24527] Training Agents Inside of Scalable World Modelsarxiv.org
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusiondiffusion-policy.cs.columbia.edu
- Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Roboticsarxiv.org
- [2603.08546] Interactive World Simulator for Robot Policy Training and Evaluationarxiv.org
- World Models | Rohit Bandarurohitbandaru.github.io
- [2301.04104] Mastering Diverse Domains through World Modelsarxiv.org
- Differentiable Robot Renderingdrrobot.cs.columbia.edu
- Introducing Reinforced Planning (RP-1)pantheon.inc
- Learning Robot World Models from Autonomous Playrobot-playworld.github.io