Year: 2025
Type: preprint
Abstract: Environments with controllable dynamics are usually understood in terms of explicit models. However, such models are not always available, but may sometimes be learned by exploring an environment. In this work, we investigate using an information measure called "predicted information gain" to determine the most informative regions of an environment to explore next. Applying methods from reinforcement learning allows good suboptimal exploring policies to be found, and leads to reliable estimates of the underlying controllable dynamics. This approach is demonstrated by comparing with several myopic exploration approaches.
Source: arXiv (Cornell University)
Authors: Loxley, Peter N., Sommer, Friedrich T.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416102606
Cites:
Cited by:
Related to: