fvalka/atc-reinforcement-learning
Reinforcement learning for an air traffic control task. OpenAI gym based simulation.
Implements a modular OpenAI Gym environment for approach control vectoring that decouples the ATC simulation from RL algorithms, enabling algorithm benchmarking across different training approaches. The simulator models realistic aviation constraints—minimum vectoring altitudes, aircraft separation, turn/descent rates—with imperial units and 2D pyglet-based rendering, while supporting extensibility to multi-aircraft scenarios, weather, and noise modeling for future research complexity.
No commits in the last 6 months.
Stars
77
Forks
21
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fvalka/atc-reinforcement-learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vietnh1009/Super-mario-bros-PPO-pytorch
Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
taherfattahi/ppo-rocket-landing
Proximal Policy Optimization (PPO) algorithm using PyTorch to train an agent for a rocket...
sdsubhajitdas/Rocket_Lander_Gym
💥💥 This is a easy installable extension for OpenAi Gym Environment. This simulates SpaceX Falcon landing.
juliankappler/lunar-lander
Implementation of deep reinforcement learning algorithms for training an agent to play the game...
anh-nn01/Lunar-Lander-Double-Deep-Q-Networks
An AI agent that use Double Deep Q-learning to teach itself to land a Lunar Lander on OpenAI universe