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.

**Keywords**: Add/Edit

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

A collection of Python modules to solve OpenAI Gym environments with Reinforcement Learning.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Teaching materials for the seminar on Application of Computational Intelligence Methods

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Deep Reinforcement Learning agent learning and playing a customized Unity game environment

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

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.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Trading Gym is an open source project for the development of reinforcement learning algorithms in the context of trading.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

This repository contains the implementation of a DDQN agent to solve the CartPole-v0 problem. I use openai gym to simulate the environment.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Solution of a first project of the deep reinforcement learning nanodegree at Udacity.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Navigation-Project: Project Nr 1 of the Deep-Reinforcement-Learning-Nanodegree of Udacity

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

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.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

TensorFlow implementation of Deep RL (Reinforcement Learning) papers based on deep Q-learning (DQN)

**Languages**: Lua Add/Edit

**Libraries**: Add/Edit

Persistent advantage learning dueling double DQN for the Arcade Learning Environment