Paper notes
World Models
First arXiv submission: · arXiv
Combines learned visual compression and recurrent dynamics with a controller, including training an agent inside a generated environment.
Contribution and setting
Demonstrates how a compact learned environment representation can support policy learning and transfer from a simulated dream to the original task.
- Model output
- Predicted latent observations, with an image decoder and task-dependent termination predictions.
- Action interface
- Actions from the controller in the studied reinforcement-learning environments.
- State and memory
- A recurrent model summarizes the history of latent observations and actions.
Relationship to NeuralOS
Cited by NeuralOS as background for learned simulation and agent training.
Scope and limitations
The model compresses observations into a latent representation for control.
Related terms: world model, recurrent dynamics, latent imagination, model-based reinforcement learning.
Cite this paper
ArXiv preprint
arXiv:1803.10122, initial submission 2018-03-27.