English text is being prepared.

Oct 28

1. 18:31

   Ma Dongxi NLP

   Dongxi NLP Explains RL Terms with a Single Example

   English text is being prepared.

   Expand summary
2. 18:25

   Ma Dongxi NLP

   Reinforcement Learning Terminology for LLM Readers: How a Single Score Is Distributed to Each Token

   The article uses DeepSeek-R1-Zero's pass@1 on AIME 2024 rising from 15.6% to 71.0% as an example to show that a rule-based judge gives only a single score for the entire response, whereas training needs to adjust the probability of each token. The author uses the sampling example "Is OpenAI open?" to explain in turn policy, state, action, reward, return, value, Q, advantage, baseline, TD error, GAE, clipping, and KL, and points out that PPO uses a critic to learn V, while GRPO uses the average score within a group to replace V.

   Expand summary