Risk Analysis
summary
A Python simulation of Risk plus a genetic algorithm produces parameterized bots whose weights evolve using TrueSkill ranking over hundreds of parallel players. The pipeline runs roughly 40 iterations over weeks on a laptop, converging to high positive territory-weight (~15) and ternary mission weight (-1/0/1). The system exposes reinforce/attack/fortify heuristics, supports mutation and crossover, and yields a best bot that beats a human after a six‑hour game; code and demo are published.
AI-written summary · about
chapters (7)
- 0:00Introduction to Risk
- 1:47How Risk works
- 4:36Risk in Python
- 13:06Genetic algorithms
- 17:20Evaluating players with TrueSkill
- 22:50Designing a genetic Risk player
- 29:25Results and conclusion
related talks
54mTeaching a Computer to Fight Itself (Implementing an OGRE AI)
31mUsing Python to build an AI to play and win SNES StreetFighter II
20mAI for Gaming: How I Built a Bot to Play a Video-Game with R and Python
36mA Data Science Approach to Systemic Risk
37mA practical perspective on training reinforcement learning bots.
32mHow I lost 1000€ betting on CS:GO with machine learning and Python
57mSolutions That Evolve: Building Self-Improving Systems with Genetic Algorithms
39mBuilding self evolving video game AI in Python