C++ implementation of the continuous LunarLander environment.

Deep Q Learning (DQN) neural net to optimize a lunar lander control policy using OpenAI Gym environment.

TensorFlow model that plays lunar lander game

React.js Planetary Lander Game

BASIC language subset/dialect in C++

Current project represents a solution of Lunar-Lander problem from OpenAI GYM library of environments. The training of agent was performed using Actor-Critic DQN model.

Programming Assignments for Reinforcement Learning Specialization

Lunar Landing using DQN and DDQN

A library for calculating Lunar Calendar in Vietnamese

Using DQN approach to resolve the LunarLander task

Using Reinforcement Learning (DQN) to train a Lunar Lander for automated landing

In this project, I created an agent using the PPO algorithm from stable baselines3 to complete a task in the LunarLander environment. The agent was trained using reinforcement learning techniques to maximize its performance in the task. The resulting model was able to achieve a high level of success in the LunarLander environment.

trial to reproduce the result mentioned in thesis

Behaviour Cloning On OpenAI Environment

Implement DQN agent on OpenAI's environment LunarLander-v2

Implementation of the DDPG algorithm to safely land a lunar lander from Gymnasium environments

AI playing Lunar Landing from python gymnasium library

A solution for LunarLander from OpenAI Gym using deep Q-Learning implemented in python using only tensorflow