This repo is for playing with reinforcement learning algorithms. I am either using openai gym or ViZDoom as an environment.
-
Updated
May 18, 2020 - Python
This repo is for playing with reinforcement learning algorithms. I am either using openai gym or ViZDoom as an environment.
This project implements an agent for playing the VizDoom game on various levels using the Proximal Policy Optimization (PPO) algorithm from the stablebaselines3 library. The agent is trained to learn the optimal actions to take at each step in the game in order to complete the level and maximize the score.
Reinforcement Learning on ViZDoom Enviroment using Advantage Actor Critic and Dueling Deep Q Networks.
Deep reinforcement learning agents that play Doom using Python.
Using Tensorflow 2.2 & 2.4 to train my bots to fight for my entertainment.
05-06 Ekim tarihlerinde gerçekleşen DeepCon konferansındaki Derin Pekiştirmeli Öğrenme Atölyesi
vizDoom AI is a study project realized by me at the 3WA, to realize this model of artificial intelligence, I was greatly inspired by the videos of Nicholas Renotte (Youtubeur that I appreciate particularly). The goal of this script is to learn how to play all levels of Doom by himself and be the best he can be.
Online exploration of memory reduction strategies of a DRL agent trained to solve a navigation task on ViZDoom
😺 Imitation Learning based on A3C algorithm 🛠
Training Deep RL agents in VizDoom.
Playing FPS Game with Supervised Learning
Convolutional Variational Autoencoder on VizdoomTakeCover
Used Vizdoom API to train AI-Bot using DQN, DRQN and add a lot of improvements fixed-Q, Dueling, Prioritzing to maximize K/D of Bot.
Applying representation learning to reinforcement learning
Add a description, image, and links to the vizdoom topic page so that developers can more easily learn about it.
To associate your repository with the vizdoom topic, visit your repo's landing page and select "manage topics."