ENTITY
Rubric-based reinforcement learning
Rubric-based reinforcement learning
PulseAugur coverage of Rubric-based reinforcement learning — every cluster mentioning Rubric-based reinforcement learning across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
HarnessRL framework enhances open-ended reinforcement learning
Researchers have developed HarnessRL, a novel framework designed to improve open-ended reinforcement learning by co-evolving a training harness alongside the policy. This approach addresses reward failure modes, such as…
-
New two-stage training method uses rubrics to boost language model performance
Researchers have introduced a novel two-stage training framework for language models that leverages rubrics for improved performance on tasks lacking exact outcome verification. The first stage, rubric-privileged on-pol…