Outcome Reward Models

Concept

Reward models trained to score the final output of a generated solution, used in test time scaling to select the best response.

Mentioned in 1 video

Videos Mentioning Outcome Reward Models

Stanford CS329A Self-Improving AI Agents | Part 2 | Test-Time Compute Scaling

Stanford CS329A Self-Improving AI Agents | Part 2 | Test-Time Compute Scaling

Stanford Online

Reward models trained to score the final output of a generated solution, used in test time scaling to select the best response.