Deep Q-Leaning trained to play Doom (openAI gym env)
-
Updated
Feb 23, 2018 - Python
Deep Q-Leaning trained to play Doom (openAI gym env)
Research about applying reinforcement learning to realitic problems. Collects data then figure out how good reinforcement learning is.
Automated Car with Reinforcement Learning. Learning is done using penalty and rewards.
Naive Q-Learning approach to self-driving cars
Dots and Boxes with reinforcement lerning
The project implements a reinforcement learning agent that can play the Space Invaders Atari game. I compare the performance of the agent using Double Deep Q-Learning with simple Deep Q-Learning.
Implement Q-Learning and DQN algorithms to solve FrozenLake problem.
Just another approach to do machine learning stuff on games.
Reinforcement Learning
Creation of grid world environment through pygame package and optimizing the motion of agent through modified q-learning process. Video can be found here: https://www.youtube.com/watch?v=-nXH8k9gRLM
A RL agent that learns to play doom's deadly corridor based on DDQN and PER.
Q-learning code, Deep Q-learning code using ChanierRL and Gym
Deep Q Learning Agent for Briscola
Reinforcement Learning with Q-learning, using Numpy and openAI Gym
A Snake AI that learns the game through Q-Learning
This repo teaches an agent to play tic-tac-toe using RayRLlib. It is still a work in progress.
Add a description, image, and links to the q-learning topic page so that developers can more easily learn about it.
To associate your repository with the q-learning topic, visit your repo's landing page and select "manage topics."