David Silver, Arthur Guez, Hado van Hasselt - 2015
Paper Links: Full-Text
Publications: arXiv Add/Edit
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
RL agent for OpenAI Gym's Lunar Lander
A collection of Python modules to solve OpenAI Gym environments with Reinforcement Learning.
Keras implementation of DQN on ViZDoom environment
Teaching materials for the seminar on Application of Computational Intelligence Methods
📖 Paper: Deep Reinforcement Learning with Double Q-learning 🕹️
Deep Reinforcement Learning agent learning and playing a customized Unity game environment
Replicating DQN papers by DeepMind for Breakout game
This repository contains the source code and documentation for the course project of the Deep Reinforcement Learning class at Northwestern University. The goal of the project was setting up an Open AI Gym and train different Deep Reinforcement Learning algorithms on the same environment to find out strengths and weaknesses for each algorithm. This will help us to get a better understanding of these algorithms and when it makes sense to use a particular algorithm or modification.
Deep Reinforcement Learning for Keras.
Double Q learning with Priortized Experience Replay
Deep Reinforcement Learning framework based on TensorFlow and OpenAI Gym
Trading Gym is an open source project for the development of reinforcement learning algorithms in the context of trading.
This repository contains the implementation of a DDQN agent to solve the CartPole-v0 problem. I use openai gym to simulate the environment.
Deep Reinforcement Learning with Self-Play
Solving the OpenAI gym environment CartPole-v1 with the DDQN algorithm
Deep Reinforcement Learning
Framework for deep reinforcement learning.
Tensorflow + OpenAI Gym implementation of Deep Q-Network (DQN), Double DQN (DDQN), Dueling Network and Deep Deterministic Policy Gradient (DDPG)
Repository for the Knot MDP
Atari - Deep Reinforcement Learning algorithms in TensorFlow
Chainer implementation of Double Deep Q-Network (Double DQN)
Catalog of reinforcement learning algorithms.
For testing out reinforcement learning things
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Deep Q-Learning Network in pytorch
Keras implementation of DQN for the MsPacman-v0 OpenAI Gym environment.
Languages: TeX Add/Edit
Overview of a Deep Reinforcement Learning method using Q-learning that recently brought the state-of-the-art results in the Atari Emulator Environment
Solution of a first project of the deep reinforcement learning nanodegree at Udacity.
Navigation-Project: Project Nr 1 of the Deep-Reinforcement-Learning-Nanodegree of Udacity
An experiment on using deep learning to play games
Highly modularized implementation of popular deep RL algorithms by PyTorch
Tensorflow Implementation for "Noisy network for exploration"
CS 294: Deep Reinforcement Learning, Spring 2017 Berkeley
Deep Double Q-Learning implementation introduced by Hasselt et al in this paper: https://arxiv.org/abs/1509.06461. It's interfacing with openAI Gym. WIP.
TensorFlow implementation of Deep Reinforcement Learning papers
Implementation of DQN for Super Mario Bros. 1-1
Simple Implementations of Important Research Papers
Languages: Lua Add/Edit
Deep reinforcement learning package for torch7
TensorFlow implementation of Deep RL (Reinforcement Learning) papers based on deep Q-learning (DQN)
Implementation of a Dueling Double Deep Q-value Network with tensorflow
DQN implementation in Keras + TensorFlow + OpenAI Gym
Languages: Lua Add/Edit
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
Rainbow: Combining Improvements in Deep Reinforcement Learning