santifiorino/dino-reinforcement-learning
Evolutionary Reinforcement Learning for Dino Game: Train an AI agent to master Google Chrome's Dino Game using a genetic algorithm and reinforcement learning.
This project helps anyone interested in seeing how artificial intelligence can learn to play a simple game without being explicitly programmed. It takes basic game information like obstacles and the dinosaur's position as input, and outputs a decision to jump or not. This is for students, hobbyists, or educators curious about genetic algorithms and reinforcement learning in a practical, visual way.
No commits in the last 6 months.
Use this if you want to understand the core mechanics of how an AI can learn through trial and error, specifically using evolutionary principles, in an accessible game environment.
Not ideal if you're looking for a production-ready game AI library or a framework to train complex, high-performance game agents.
Stars
90
Forks
29
Language
Processing
License
—
Category
Last pushed
Aug 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/santifiorino/dino-reinforcement-learning"
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