Tag
Reinforcement Learning (RL)
Every Reinforcement Learning (RL) story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.
Week 30 · 2026
Read the issue →-
On-Policy Delta Distillation
This research presents OPD2, a novel distillation technique that focuses on the learning trajectory of reasoning models by using a delta signal between teacher and base models. Experimental results prove it outperforms standard on-policy distillation across multiple complex reasoning domains.
-
On-Policy Delta Distillation
This research presents OPD2, a novel distillation technique that focuses on the learning trajectory of reasoning models by using a delta signal between teacher and base models. Experimental results prove it outperforms standard on-policy distillation across multiple complex reasoning domains.
Week 29 · 2026
Read the issue →-
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
The Seed framework addresses the limitations of sparse rewards in agentic reinforcement learning by extracting reusable skills from completed interaction trajectories. It utilizes on-policy distillation to provide dense, token-level supervision that evolves alongside the policy's capabilities.
-
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
The Seed framework addresses the limitations of sparse rewards in agentic reinforcement learning by extracting reusable skills from completed interaction trajectories. It utilizes on-policy distillation to provide dense, token-level supervision that evolves alongside the policy's capabilities.
Free weekly digest
Get next Saturday’s issue in your inbox
The week’s most relevant AI, security, blockchain, and engineering stories — curated, summarised, and reviewed by humans. No spam, unsubscribe anytime.
Subscribe — it’s free