Presented by
90/30 Club
We meet weekly in-person to talk about new ML papers! Come and join the discussion!
Hosted By
34 Went
90/30 Club (ML reading) #16: Policy to Reasoning
Registration
Past Event
About Event
Week 16: Policy to Reasoning
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Additional Readings:
- Deep Reinforcement Learning: Pong from Pixels
- The State of Reinforcement Learning for LLM Reasoning
- Group Relative Policy Optimization (GRPO) Illustrated Breakdown
Google Drive for sharing Comments✍
Discussion at 20:00, (optional) quiet reading from 19:00.
Presented by
90/30 Club
We meet weekly in-person to talk about new ML papers! Come and join the discussion!
Hosted By
34 Went