world-model-planner / README.md
Vikingdude81's picture
Upload folder using huggingface_hub
0e97e2c verified
metadata
title: Robust World Model Planner
emoji: 
colorFrom: indigo
colorTo: blue
sdk: static
pinned: false
license: mit
short_description: Interactive world model planning simulation

⚡ Robust World Model Planner

An interactive visualization comparing different world model approaches for robot navigation and planning.

What Is This?

This demo illustrates concepts from the paper "Closing the Train-Test Gap for Gradient-Based World Model Planning". It shows how different world model training strategies affect an agent's ability to navigate obstacle-rich environments.

The Three Models

Model Description Color
STANDARD_DINO Baseline frozen encoder - noisy gradients 🟣 Fuchsia
ONLINE_WM Online fine-tuning - moderate improvement 🔵 Blue
ADVERSARIAL_WM Adversarial training - smooth, robust 🔵 Cyan

Key Concepts

  • Steering Gain: How strongly the agent avoids obstacles
  • Scan Horizon: How far ahead the agent "sees" (lookahead radius)
  • Loss Surface: Adversarial training smooths the optimization landscape
  • Gradient Field: Visualize the planning gradients across the map

How To Use

  1. Select a Model from the sidebar (try Adversarial for best results)
  2. Choose an Environment (Simple → Wall → Complex)
  3. Click "Execute" to start navigation
  4. Click anywhere on the map to set a new target
  5. Toggle "Matrix_View" to see the gradient field
  6. Explore tabs: Live Feed, Data Surface (loss landscape), Analytics (benchmarks)

Why Adversarial?

Standard world models have noisy, non-convex loss surfaces that make gradient-based planning unreliable. Adversarial training:

  • ✅ Smooths the loss landscape
  • ✅ Provides consistent gradients
  • ✅ Enables reliable obstacle avoidance
  • ✅ Closes the train-test gap

Based on research: Closing the Train-Test Gap | Built with React + Recharts