Update README.md

README.md

@@ -14,11 +14,18 @@ base_model:
 
 # Model Card
 
-This is a pure reinforcement learning (RL) experiment applied to an open-domain task: creative advertisement generation.
+Unlike the impressive DeepSeek-R1(-Zero), this project focuses on a pure reinforcement learning (RL) experiment applied to an open-domain task: creative advertisement generation.
 
-**Objective:** To explore the feasibility of applying R1-like methods to an open-domain task without a verifiable ground-truth reward, at the very least demonstrating its potential.
+**Objective:**
 
-**Note**: Despite its small size, the resulting model demonstrates intriguing generative capabilities—though it's still **far from perfect**.
+- To investigate the feasibility of applying R1-like methods to an open-domain task without a verifiable ground-truth reward, while at least demonstrating its potential.
+- To explore whether `<think>` and `<answer>` rewards can be explicitly designed to provide strong guidance through RL based on human prior knowledge.
+
+**Note**:
+
+- Our goal is **not** to induce self-reflective thinking, but to align with human thought processes purely through RL, without any supervised fine-tuning (SFT) on any constructed dataset.
+
+Despite its small size, the resulting 1.5B-GRPO model demonstrates intriguing generative capabilities—though it's still **far from perfect**.
 
 ## Quick start