rembertdesigns/pit-stop-simulator
An interactive F1 race simulator using Reinforcement Learning (PPO, Q-learning) and Streamlit to optimize pit stop strategies based on dynamic conditions.
Implements dual RL agents—Q-Learning with discretized state space for fast tabular inference and PPO with neural networks for continuous observation handling—enabling real-time pit stop decisions across dynamic weather, traffic, and safety car conditions. The physics engine models compound-specific tire degradation, fuel load effects, and FIA regulation compliance within a high-fidelity race environment. Deployed as an interactive Streamlit web app with comparative performance analytics across 100+ simulation runs.
Stars
9
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rembertdesigns/pit-stop-simulator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JaideepGuntupalli/f1-predictor
🏎️ A machine-learning approach to predict Formula 1 Grand Prix race outcomes.
Jared-Chan/f1ml
Formula One Race Lap-by-Lap Prediction with Machine Learning
VforVitorio/F1_Strat_Manager
AI Models for Strategy Recommendations in Formula 1 races. Final Thesys Project of UIE...
shameeh/F1-Predictive-Analytics-Architecture
This project ingests live Formula 1 telemetry, processes it through a highly scalable Medallion...
hugomagee/OptimalAthlete
ML system predicting 400m sprint times (R²=0.84) — trained on 18 months of personal race & training data