---
title: GameTheory-Solver Demo
emoji: 🎯
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.14.0
app_file: app.py
pinned: true
license: apache-2.0
short_description: AI game theory solver with step-by-step reasoning
tags:
- game-theory
- nash-equilibrium
- mathematics
- economics
- qwen2.5
- qlora
- grpo
- reinforcement-learning
- reasoning
- demo
models:
- Alogotron/GameTheory-Reasoner
- 2reb/GameTheory-Solver
datasets:
- 2reb/GameTheory-Bench
---

# 🎯 GameTheory-Reasoner Demo

**An interactive demo for the [GameTheory-Reasoner](https://huggingface.co/Alogotron/GameTheory-Reasoner) model — a Qwen2.5-7B trained through SFT + GRPO reinforcement learning with verifiable rewards to solve game theory problems with enhanced step-by-step reasoning.**

[![Reasoner](https://img.shields.io/badge/🤗_Reasoner-GameTheory--Reasoner-purple)](https://huggingface.co/Alogotron/GameTheory-Reasoner)
[![Solver](https://img.shields.io/badge/🤗_Solver-GameTheory--Solver-orange)](https://huggingface.co/2reb/GameTheory-Solver)
[![Dataset](https://img.shields.io/badge/📊_Dataset-GameTheory--Bench-yellow)](https://huggingface.co/datasets/2reb/GameTheory-Bench)
[![License](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)

---

## ✨ Features

- 🔍 **Browse Examples** — Explore 100 curated problems from the [GameTheory-Bench](https://huggingface.co/datasets/2reb/GameTheory-Bench) dataset across all 10 categories
- 🧠 **Solve Your Own** — Enter any game theory problem and get an AI-generated solution via the HuggingFace Inference API
- 📊 **10 Problem Categories** — From 2×2 matrix games to mechanism design

## 🎮 Supported Problem Types

| Category | Solution Concepts |
|---|---|
| **Normal Form Games** (2×2 → 4×4) | Nash Equilibria (pure & mixed), dominant strategies, IESDS |
| **Zero-Sum Games** | Minimax theorem, saddle points, mixed strategies |
| **Sequential Games** | Backward induction, subgame perfect equilibrium |
| **Auction Theory** | Bayesian Nash equilibrium bidding, revenue equivalence |
| **Bayesian Games** | BNE, type spaces, signaling, separating/pooling equilibria |
| **Cooperative Games** | Shapley value, core, nucleolus |
| **Mechanism Design** | VCG, incentive compatibility, revelation principle |

## 📈 Model Performance: Base → Solver → Reasoner

| Metric | Base (82%) | Solver (Phase 1 SFT) | Reasoner (Phase 2 GRPO) |
|---|:---:|:---:|:---:|
| **Overall Accuracy** | 82% | **94%** | **94%** |
| **Hard Problems** | 66.7% | 94.4% | **94.4%** |
| **Reasoning Quality** | 0.48 | 0.51 | **0.54 (+6%)** |
| Bayesian Games | 0% | 100% | **100%** |
| Mechanism Design | 60% | 100% | **100%** |

> Phase 2 uses **GRPO (Group Relative Policy Optimization)** with verifiable rewards, achieving the same 94% accuracy while producing +6% better reasoning quality.

## 🔗 Links

- 🧠 **Reasoner (Phase 2)**: [Alogotron/GameTheory-Reasoner](https://huggingface.co/Alogotron/GameTheory-Reasoner)
- 🤖 **Solver (Phase 1)**: [2reb/GameTheory-Solver](https://huggingface.co/2reb/GameTheory-Solver)
- 📊 **Dataset**: [2reb/GameTheory-Bench](https://huggingface.co/datasets/2reb/GameTheory-Bench) (2,913 verified problems)
- 🏠 **Base Model**: [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)