Scaling laws for reward model overoptimization
Published 2022-10-19T07:00:00Z•1a032a768300cb63fd31ac90bb4a36fab5ad3d67c5e8fd5b2714045bbe68ad64
Source metadata
- Publication date
- 2022-10-19T07:00:00Z
- Source identifier
- https://openai.com/index/scaling-laws-for-reward-model-overoptimization
- Public record ID
- record:sha256:1a032a768300cb63fd31ac90bb4a36fab5ad3d67c5e8fd5b2714045bbe68ad64
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- openai_research
- Record identifier
- 1a032a768300cb63fd31ac90bb4a36fab5ad3d67c5e8fd5b2714045bbe68ad64
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.