Upload folder using huggingface_hub

README.md

@@ -4,7 +4,7 @@ emoji: 🧠
 colorFrom: blue
 colorTo: green
 sdk: gradio
-sdk_version: 4.36.0
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
 tags:
@@ -12,16 +12,25 @@ tags:
   - reinforcement-learning
   - planning
   - ai-education
+  - cognitive-architecture
 ---
 
-# 🧠 World Model Demo
+# World Model Demo
 
-Interactive demonstration of world model concepts in AI planning.
+Interactive visualization of model-based reinforcement learning concepts, inspired by architectures like MuZero and Dreamer.
 
 ## Features
-- Visual grid environment with agent, goal, and obstacles
-- Phase-based learning cycle (Observe → Predict → Act → Learn)
-- Real-time model accuracy tracking
-- Educational visualization of AI planning
 
-Built for exploring model-based reinforcement learning concepts.
+- **Mental Simulation**: Watch the AI plan ahead by imagining future states
+- **Tree Search Visualization**: See how different action sequences are evaluated  
+- **Configurable Environment**: Adjust grid size and obstacles
+- **Step-by-Step Mode**: Understand each phase of the planning process
+
+## How It Works
+
+1. **Observe**: Agent perceives current grid state
+2. **Imagine**: World model predicts outcomes of possible actions
+3. **Plan**: Tree search evaluates action sequences
+4. **Act**: Best action is selected and executed
+
+This demonstrates key concepts from model-based RL without requiring actual neural networks.

requirements.txt

@@ -1 +1 @@
-gradio>=5.0.0
+# Dependencies managed by sdk_version in README.md