Verifiably safe exploration for end-to-end reinforcement learning (Q6201597)
From MaRDI portal
scientific article; zbMATH DE number 7807687
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Verifiably safe exploration for end-to-end reinforcement learning |
scientific article; zbMATH DE number 7807687 |
Statements
Verifiably safe exploration for end-to-end reinforcement learning (English)
0 references
21 February 2024
0 references
differential dynamic logic
0 references
formal verification
0 references
hybrid systems
0 references
neural networks
0 references
reinforcement learning
0 references
safe artificial intelligence
0 references
