Meraj Mammadov's repositories
f1tenth_reinforcement_learning
PPO RL agent for F1TENTH racing, simulation and experiment
rl_algorithms
PyTorch Implementations of some of the Reinforcement Learning algorithms from scratch.
tictactoe-reinforcement-learning
Using Tabular RL, Value Iteration to train a tic-tac-toe agent
meraccos.github.io
Website
ModelicaDynamicORC
Dynamic Simulation of ORC (Organic Rankine Cycle) in Modelica
Clean-Language-Models
Clean implementations of several language models from scratch, in Pytorch
f1tenth_rl
PPO training of F1TENTH racing simulation
gym-pybullet-drones
PyBullet Gym environments for single and multi-agent reinforcement learning of quadcopter control
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
pytorch_sac_ae
PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)
random_car_racing_track_generator
This repository contains the Python code to randomly generate car racing track.