Deep Q-Learning agent learns how to navigate a world full of bananas. Part of the coursework for Udacity's Deep RL Nanodegree.
-
Updated
Sep 7, 2021 - Jupyter Notebook
Deep Q-Learning agent learns how to navigate a world full of bananas. Part of the coursework for Udacity's Deep RL Nanodegree.
This repo contains all the praticals/homeworks assigned during the Reinforcement Learning course held by Prof. Roberto Capobianco at the AI & Robotics Master's Degree at University of Sapienza @ Rome, Italy.
Propose fully convolutional network with skip connection which is deeper than the network used in vanilla DQN.
A complete MataLab laboratory for training and evaluating EMG HGR RL DQN and DDQN models.
Value Based and policy gradient Algorithms Implementation on single and multi agent environments.
A collection of AIs made with PyTorch
Lunar Landing using DQN and DDQN
Sandbox for Deep Reinforcement Learning Algorithms
Donkey Kong AI(DDQN, RL, NEAT).University group project for Artificial Intelligence (third-year course)
controlling an inverted pendulum using DQN , DDQN and PID controller in gym environment.
Double deep q network implementation in OpenAI Gym's "Mountain Car" environment
Implementation of the Double Deep Q-Learning algorithm with a prioritized experience replay memory to train an agent to play the minichess variante Gardner Chess
A comparision between the performances of DQN and several of its variants using PyTorch and Pong.
This project trains an agent to navigate and to collect bananas in a continuous square environment. The environment is based on the Unity Machine Learning Agents Toolkit
Genetic algorithm to select the weights of a MLP to play lunar lander using Reinforcement Learning.
Add a description, image, and links to the ddqn topic page so that developers can more easily learn about it.
To associate your repository with the ddqn topic, visit your repo's landing page and select "manage topics."