Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective (Q6182771): Difference between revisions
From MaRDI portal
Created a new Item |
Added link to MaRDI item. |
||
| links / mardi / name | links / mardi / name | ||
Revision as of 07:02, 10 July 2024
scientific article; zbMATH DE number 7795126
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective |
scientific article; zbMATH DE number 7795126 |
Statements
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective (English)
0 references
26 January 2024
0 references
AGI safety
0 references
reinforcement learning
0 references
Bayesian learning
0 references
causality
0 references
decision theory
0 references
causal influence diagrams
0 references
