Update README.md

README.md

@@ -27,13 +27,15 @@ The goal is to study **human behaviour in supply chain decision-making** when co
 
 ## 📊 Features
 
-- Classic Beer Game with **24 weeks**, including a **demand shock at week 6**.  
-- Distributor inputs weekly order quantity; AI agents respond automatically.  
-- Optional **Information Sharing** toggle: reveal historical customer demand to all roles.  
-- Multi-participant support: each participant gets a unique **participant ID** and **per-participant CSV log**.  
-- Rich **data logging**: timestamps, inventory, backlog, orders, info-sharing toggles, and raw AI output.  
-- Local CSV export & optional **cloud upload** (S3) for persistent storage.
-
+- Classic Beer Game settings:
+  - 36 weeks simulation
+  - 2-week shipping delay
+  - 1-week information delay
+  - Standard customer demand sequence (constant → shock → fluctuations)
+- Human plays as Distributor, other roles are LLM agents.
+- Logs saved **per participant** and automatically pushed to Hugging Face Datasets Hub.
+- Simple Streamlit interface, deployable on Hugging Face Spaces.
+- 
 ---
 
 ## 🛠️ Running the Experiment