Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
- multi-task
|
| 7 |
- scout
|
| 8 |
- ppo
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
# SCOUT-Multitask Sequential RL Agent
|
|
@@ -51,4 +53,8 @@ model_name = "Harryis/SCOUT_multitask"
|
|
| 51 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 52 |
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
| 53 |
|
| 54 |
-
# Example: Prompt the model for a Sudoku move or Sokoban action
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- multi-task
|
| 7 |
- scout
|
| 8 |
- ppo
|
| 9 |
+
papers:
|
| 10 |
+
- 2601.21754
|
| 11 |
---
|
| 12 |
|
| 13 |
# SCOUT-Multitask Sequential RL Agent
|
|
|
|
| 53 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 54 |
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
| 55 |
|
| 56 |
+
# Example: Prompt the model for a Sudoku move or Sokoban action
|
| 57 |
+
|
| 58 |
+
**Links:**
|
| 59 |
+
- 📄 **Paper:** [SCOUT: Sequential RL with Exploration & Distillation](https://huggingface.co/papers/2601.21754)
|
| 60 |
+
- 💻 **Code:** [Github](https://github.com/Harry-mic/SCOUT)
|