Update README.md
Browse files
README.md
CHANGED
|
@@ -1,19 +1,65 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
-
sdk:
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
- streamlit
|
| 10 |
pinned: false
|
| 11 |
-
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
-
|
|
|
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Beer Game Experiment
|
| 3 |
+
emoji: 🍺
|
| 4 |
+
colorFrom: purple
|
| 5 |
+
colorTo: green
|
| 6 |
+
sdk: streamlit
|
| 7 |
+
sdk_version: 1.32.0
|
| 8 |
+
app_file: app.py
|
|
|
|
| 9 |
pinned: false
|
| 10 |
+
license: mit
|
| 11 |
+
python_version: "3.10"
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# 🍺 Beer Game — Human & AI Collaboration
|
| 15 |
|
| 16 |
+
This is a **Beer Game experiment interface** built with **Streamlit** and hosted on Hugging Face Spaces.
|
| 17 |
+
The goal is to study **human behaviour in supply chain decision-making** when collaborating with AI agents (Factory, Wholesaler, Retailer powered by OpenAI GPT-4o-mini).
|
| 18 |
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
## 🎮 Roles
|
| 22 |
+
|
| 23 |
+
- **Distributor**: Human participant — you control the order quantity each week.
|
| 24 |
+
- **Factory / Wholesaler / Retailer**: AI agents making decisions using LLMs.
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
## 📊 Features
|
| 29 |
+
|
| 30 |
+
- Classic Beer Game with **24 weeks**, including a **demand shock at week 6**.
|
| 31 |
+
- Distributor inputs weekly order quantity; AI agents respond automatically.
|
| 32 |
+
- Optional **Information Sharing** toggle: reveal historical customer demand to all roles.
|
| 33 |
+
- Multi-participant support: each participant gets a unique **participant ID** and **per-participant CSV log**.
|
| 34 |
+
- Rich **data logging**: timestamps, inventory, backlog, orders, info-sharing toggles, and raw AI output.
|
| 35 |
+
- Local CSV export & optional **cloud upload** (S3) for persistent storage.
|
| 36 |
+
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
## 🛠️ Running the Experiment
|
| 40 |
+
|
| 41 |
+
### 1. On Hugging Face Spaces
|
| 42 |
+
1. Deploy this repo as a **Streamlit Space**.
|
| 43 |
+
2. Add **Secrets** (Settings → Secrets):
|
| 44 |
+
- `OPENAI_API_KEY` — your OpenAI API key
|
| 45 |
+
- Optional for S3 export:
|
| 46 |
+
- `AWS_ACCESS_KEY_ID`
|
| 47 |
+
- `AWS_SECRET_ACCESS_KEY`
|
| 48 |
+
- `S3_BUCKET`
|
| 49 |
+
- `S3_REGION` (default: `us-east-1`)
|
| 50 |
+
|
| 51 |
+
3. Participants open the Space and either:
|
| 52 |
+
- Enter a custom **participant ID**, or
|
| 53 |
+
- Use the **auto-generated ID** shown in the app.
|
| 54 |
+
|
| 55 |
+
Example URL with participant ID:
|
| 56 |
+
|
| 57 |
+
https://huggingface.co/spaces/<user>/<space>?participant_id=ABC123
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### 2. Locally
|
| 63 |
+
```bash
|
| 64 |
+
pip install -r requirements.txt
|
| 65 |
+
streamlit run app.py
|