Self Parking Agents with Reinforcement Learning
This repository contains experiments on self-parking using custom environments created from highway-env and trained using TQC from stable-baselines3.
A goal-conditioned continuous control task in which the ego-vehicle must park in a given space with the appropriate heading.
 2 rows with walls |
 4 rows |
 6 rows |
 6 rows all cars |
 Additional Obstacles |
 Random agent location |
Simulation results
