Rishabh Agarwal
Source-listed: Founding member · Periodic Labs
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Deep Reinforcement Learning at the Edge of the Statistical PrecipiceSaved credit: Contributor · 2021Explore people connected to this work →
- Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate ProgressSaved credit: Contributor · 2022Explore people connected to this work →
- On-Policy Distillation of Language Models: Learning from Self-Generated MistakesSaved credit: Contributor · 2024Explore people connected to this work →
- Training Language Models to Self-Correct via Reinforcement LearningSaved credit: Contributor · 2025Explore people connected to this work →
- Gemma 2: Improving Open Language Models at a Practical SizeSaved credit: Contributor · 2024Explore people connected to this work →