joynnayvedya/disaster-response-trained

Title: Teaching an LLM to Triage Disasters: Building an RL Environment with OpenEnv Tags: openenv reinforcement-learning disaster-response grpo qwen

markdown# Teaching an LLM to Triage Disasters 🚨

The Problem

During a natural disaster, Emergency Operations Centers (EOCs) are overwhelmed by thousands of frantic incident reports. A flooded neighborhood, a chemical plant fire, a hospital wing collapse — all arriving simultaneously. Human coordinators must instantly decide: which team? what priority? what action?

We built an AI agent that does exactly this.

The Environment

We built Disaster Response Coordination OpenEnv — a multi-step RL environment where an AI agent acts as an Emergency Incident Commander.

15 real-world scenarios across 3 difficulty tiers, modeled after actual disasters:

• —🌊 2018 Kerala Floods → dam spillway overflow, communication blackouts
• —☠️ 2020 Vizag Gas Leak → chemical plant fire, toxic plume evacuation
• —⚡ 2012 North India Grid Failure → cold-chain medicine failures, hospital blackouts

Action Space

For every incident ticket, the agent must complete a 4-step workflow: classify → setpriority → draftreply → submit_ticket

Reward Function

reward = 0.40 × teamrouting + 0.30 × priority + 0.30 × replyquality

Dense, partial rewards at every step. No sparse end-of-episode signals.

Difficulty Scaling

Training with GRPO

We trained Qwen2.5-7B-Instruct using GRPO (Group Relative Policy Optimization) via TRL + Unsloth on a Google Colab T4 GPU.

Setup:

• —Base model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
• —Algorithm: GRPOTrainer (TRL)
• —LoRA: r=16, 4-bit quantization
• —Epochs: 3 | Steps: 14
• —Reward: Live environment feedback via HF Space API

The reward function connected directly to our live HF Space — every training step sent real incident prompts to the environment and received real rewards back.

Training Reward Curve

[image]

What We Discovered: Sparse Reward Collapse

The untrained base model immediately revealed why this environment is hard:

Before training, the model hallucinated invalid outputs: team: "emergency_services" ❌ (not a valid team) team: "utility repair" ❌ priority: "very-high" ❌ (not a valid priority) priority: "higher" ❌

After training, the model learned valid action spaces: team: "rescue" ✅ priority: "urgent" ✅

However, we observed sparse reward collapse — a known RL failure mode where a small model (7B at 4-bit) struggles to optimize across a multi-step workflow with interdependent rewards. This validates our environment's quality: it is genuinely difficult enough to expose real RL failure modes that larger models or longer training runs would be needed to overcome.

Baseline Results

All 3 difficulty tiers passed (score ≥ 0.6).

The Dashboard

We built a military-style tactical command dashboard with:

• —🗺️ Live OpenStreetMap incident markers with radar pulse animations
• —⚡ ARIA — AI Incident Analyst (Gemini-powered, analyses any incident live)
• —📊 Real-time score tracking, threat level bar, team routing
• —🔔 Operations feed with meaningful event notifications

[image]

Links

Try It Yourself

git clone https://github.com/letsjoyn/meta-scalar-hack.git
cd meta-scalar-hack
pip install -e .
py inference.py

Built for the 2026 Meta & Scalar AI Hackathon — Grand Finale, Bangalore.

Uploaded finetuned model

• —Developed by: joynnayvedya
• —License: apache-2.0
• —Finetuned from model : unsloth/Qwen2.5-7B-Instruct-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>