Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
Saved in:
| Title: | Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective. |
|---|---|
| Authors: | Everitt, Tom1,2, tomeveritt@google.com, Hutter, Marcus1,2, Kumar, Ramana1, Krakovna, Victoria1 |
| Source: | Synthese; Nov2021 Supplement 27, Vol. 198 Issue 27, p6435-6467, 33p |
| Database: | Humanities Source |
| ISSN: | 00397857 |
|---|---|
| DOI: | 10.1007/s11229-021-03141-4 |
