alextousss/wargames
Two agents shooting at each other, controlled by a neural network optimized with a genetic algorithm.
This project simulates two AI agents learning to fight each other in a virtual arena without human intervention. By inputting their relative distance, angle, and time since the last shot, the agents' neural networks evolve through a genetic algorithm to determine their next action. This tool is for anyone interested in observing artificial intelligence self-learn complex combat strategies.
No commits in the last 6 months.
Use this if you are exploring how AI agents can develop emergent behaviors and combat skills solely through simulated experience and evolutionary processes.
Not ideal if you need a pre-trained, robust AI for a specific game or a system where human-defined rules or supervised learning are required.
Stars
24
Forks
2
Language
Python
License
—
Category
Last pushed
Dec 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/alextousss/wargames"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
gtri/scrimmage
Multi-Agent Robotics Simulator